{ "complete": true, "report": { "bucket": "emo_Amusement", "label": "Intense Amusement", "definition": { "id": "emo_Amusement", "category": "emotion", "head": "emo_Amusement", "pole": "high", "label": "Intense Amusement", "floor": 3.0 }, "recipe_status": "direct_manual_recipe", "manual_provenance": [ { "id": "rank4/emotion_amusement/full-v2-sealed/sealed-selected", "mission": "emotion_amusement", "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": 6.351440253257752, "genuineness": 4.2052499127388, "wer": 0.005913455794504182, "identity": 0.5802535837888718, "voiceclap": -0.0684474213514477, "fitness": 0.7902671323162713, "steering_v2": 0.9215175363787085, "raw_target": 1.9037910464406014, "target_cdf": 0.9215175363787085, "family_hit_all": null, "nominal_hit_all": null, "n": 100, "valid_fraction": 1, "by_arm": { "reference": { "n": 50, "ce": 6.3487397480010985, "genuineness": 4.1577088832855225, "wer": 0.0038723118279569892, "identity": 0.5802535837888718, "fitness": 0.7989521837480483, "steering_v2": 0.9400582669429819 }, "none": { "n": 50, "ce": 6.354140758514404, "genuineness": 4.252790942192077, "wer": 0.007954599761051374, "identity": null, "fitness": 0.7815820808844943, "steering_v2": 0.902976805814435 } } } } ], "selected_wording": { "id": "manual-eef73ce58f32", "general": "Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.", "inline": [ "Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.", "Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.", "Let the final sound trail off with a lingering, cheerful vocal brightness." ], "cfg": 3, "recipe": "P06", "strategy": "local-Gemma-mutation", "timing_syntax": "canonical", "canonical_labels": true, "neutral_event": "keep", "parent": "cfg-3", "origin": "exact_frozen_manual_recipe" }, "selection": { "manual_no_adapter": { "config": { "scale": 0.0, "cfg": 1.5 }, "n": 20, "target_z": 1.4888671869901453, "target_raw": 1.7695671260356902, "ce": 6.192983937263489, "genuineness": 4.230573737621308, "identity": 0.5350954897701741, "wer": 0.005409356725146199, "valid_fraction": 1, "identity_delta": -0.04093891754746437, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, "manual_adapter": { "config": { "scale": 0.75, "cfg": 2.0 }, "n": 20, "target_z": 1.9066405955357626, "target_raw": 2.1320504784584045, "ce": 6.202117991447449, "genuineness": 4.1853862524032595, "identity": 0.537373562157154, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.03866084516048431, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, "grid": [ { "config": { "scale": 0.0, "cfg": 1.5 }, "n": 20, "target_z": 1.4888671869901453, "target_raw": 1.7695671260356902, "ce": 6.192983937263489, "genuineness": 4.230573737621308, "identity": 0.5350954897701741, "wer": 0.005409356725146199, "valid_fraction": 1, "identity_delta": -0.04093891754746437, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.25 }, "n": 20, "target_z": 1.3119140538861382, "target_raw": 1.616032785177231, "ce": 6.18424699306488, "genuineness": 4.291765129566192, "identity": 0.544018542766571, "wer": 0.0027777777777777775, "valid_fraction": 1, "identity_delta": -0.03201586455106735, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.0 }, "n": 20, "target_z": 1.1566650273459038, "target_raw": 1.4813301295042038, "ce": 6.1961609601974486, "genuineness": 4.257246863842011, "identity": 0.527236919850111, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.04879748746752739, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 5.0 }, "n": 20, "target_z": 2.5421874401054843, "target_raw": 2.6834861278533935, "ce": 6.1048202276229855, "genuineness": 4.037114822864533, "identity": 0.425974899623543, "wer": 0.02361519607843137, "valid_fraction": 1, "identity_delta": -0.15005950769409537, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 4.0 }, "n": 20, "target_z": 2.383203060114275, "target_raw": 2.545542472600937, "ce": 6.079602217674255, "genuineness": 4.060336148738861, "identity": 0.5082053549587726, "wer": 0.0061111111111111106, "valid_fraction": 1, "identity_delta": -0.06782905235886574, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 3.0 }, "n": 20, "target_z": 2.131249957923566, "target_raw": 2.326934003829956, "ce": 6.132023930549622, "genuineness": 4.13172607421875, "identity": 0.48050418347120283, "wer": 0.015073529411764706, "valid_fraction": 0.95, "identity_delta": -0.09553022384643554, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 2.5 }, "n": 20, "target_z": 1.8628906255903581, "target_raw": 2.0940905809402466, "ce": 6.175510025024414, "genuineness": 4.104425323009491, "identity": 0.5137890562415123, "wer": 0.006666666666666666, "valid_fraction": 1, "identity_delta": -0.062245351076126096, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 2.0 }, "n": 20, "target_z": 1.7699218759123716, "target_raw": 2.0134257435798646, "ce": 6.2203861474990845, "genuineness": 4.188838028907776, "identity": 0.4693104363977909, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.10672397091984749, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 2.0 }, "n": 20, "target_z": 1.9066405955357626, "target_raw": 2.1320504784584045, "ce": 6.202117991447449, "genuineness": 4.1853862524032595, "identity": 0.537373562157154, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.03866084516048431, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 2.0 }, "n": 20, "target_z": 1.6072265536714625, "target_raw": 1.8722622692584991, "ce": 6.166773080825806, "genuineness": 4.108818602561951, "identity": 0.5331503048539161, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.04288410246372223, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.5 }, "n": 20, "target_z": 1.5957031408323317, "target_raw": 1.8622639179229736, "ce": 6.212840580940247, "genuineness": 4.2296323537826535, "identity": 0.555020734667778, "wer": 0.003333333333333333, "valid_fraction": 1, "identity_delta": -0.02101367264986038, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.0 }, "n": 20, "target_z": 1.1242187728629602, "target_raw": 1.4531779617071152, "ce": 6.1878211975097654, "genuineness": 4.251912260055542, "identity": 0.5327992729842663, "wer": 0.003333333333333333, "valid_fraction": 1, "identity_delta": -0.043235134333372116, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.0 }, "n": 20, "target_z": 0.9853515583943275, "target_raw": 1.3326890736818313, "ce": 6.203706526756287, "genuineness": 4.262581551074982, "identity": 0.5495532542467118, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.026481153070926668, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 5.0 }, "n": 20, "target_z": 2.666796816232532, "target_raw": 2.7916041254997253, "ce": 6.084963583946228, "genuineness": 3.930108344554901, "identity": 0.40309954099357126, "wer": 0.027448830409356723, "valid_fraction": 0.95, "identity_delta": -0.17293486632406713, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 5.0 }, "n": 20, "target_z": 2.5601562000879037, "target_raw": 2.6990768194198607, "ce": 5.9537108659744264, "genuineness": 3.9497209429740905, "identity": 0.4078939359635115, "wer": 0.008596491228070175, "valid_fraction": 1, "identity_delta": -0.16814047135412694, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 5.0 }, "n": 20, "target_z": 2.4730468531567493, "target_raw": 2.6234959244728087, "ce": 5.97535469532013, "genuineness": 3.998517191410065, "identity": 0.34389891289174557, "wer": 0.01637426900584795, "valid_fraction": 1, "identity_delta": -0.23213549442589282, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 4.0 }, "n": 20, "target_z": 2.4640624456870523, "target_raw": 2.6157005548477175, "ce": 6.064511179924011, "genuineness": 4.02911285161972, "identity": 0.48134947568178177, "wer": 0.005555555555555555, "valid_fraction": 1, "identity_delta": -0.09468493163585663, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 4.0 }, "n": 20, "target_z": 2.455078100043952, "target_raw": 2.607905238866806, "ce": 6.019237947463989, "genuineness": 3.9629006385803223, "identity": 0.4346299558877945, "wer": 0.005756578947368421, "valid_fraction": 1, "identity_delta": -0.1414044514298439, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 4.0 }, "n": 20, "target_z": 2.4121092954089907, "target_raw": 2.5706231236457824, "ce": 6.10601167678833, "genuineness": 4.008401906490326, "identity": 0.4351188078522682, "wer": 0.019972265221878224, "valid_fraction": 1, "identity_delta": -0.1409155994653702, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 3.0 }, "n": 20, "target_z": 2.2523437294984725, "target_raw": 2.432001668214798, "ce": 6.1107773065567015, "genuineness": 4.056570529937744, "identity": 0.4695412181317806, "wer": 0.01423611111111111, "valid_fraction": 0.95, "identity_delta": -0.10649318918585778, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 3.0 }, "n": 20, "target_z": 2.24335930141991, "target_raw": 2.424206280708313, "ce": 6.138378071784973, "genuineness": 4.024719643592834, "identity": 0.49936328530311586, "wer": 0.005555555555555555, "valid_fraction": 1, "identity_delta": -0.07667112201452256, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 3.0 }, "n": 20, "target_z": 2.107812443110944, "target_raw": 2.3065983176231386, "ce": 6.104025959968567, "genuineness": 3.9936532378196716, "identity": 0.46370275542140005, "wer": 0.011458333333333333, "valid_fraction": 1, "identity_delta": -0.11233165189623832, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 2.5 }, "n": 20, "target_z": 1.976562478317756, "target_raw": 2.192718577384949, "ce": 6.1479092836380005, "genuineness": 4.09406988620758, "identity": 0.5028541132807731, "wer": 0.0027777777777777775, "valid_fraction": 1, "identity_delta": -0.07318029403686524, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 2.5 }, "n": 20, "target_z": 1.9027343705454796, "target_raw": 2.128661221265793, "ce": 6.165581727027893, "genuineness": 4.071476101875305, "identity": 0.4953208059072495, "wer": 0.005555555555555555, "valid_fraction": 1, "identity_delta": -0.08071360141038894, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 2.5 }, "n": 20, "target_z": 1.8169921951478212, "target_raw": 2.054266560077667, "ce": 6.140363717079163, "genuineness": 4.103797769546508, "identity": 0.492887008190155, "wer": 0.008596491228070175, "valid_fraction": 1, "identity_delta": -0.08314739912748337, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 2.0 }, "n": 20, "target_z": 1.7707031442671426, "target_raw": 2.014103615283966, "ce": 6.18424699306488, "genuineness": 4.11321177482605, "identity": 0.4714847728610039, "wer": 0.013333333333333332, "valid_fraction": 0.95, "identity_delta": -0.10454963445663452, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.25 }, "n": 20, "target_z": 1.5716796781884423, "target_raw": 1.841419830918312, "ce": 6.230314493179321, "genuineness": 4.264778101444245, "identity": 0.5044987119734288, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.07153569534420967, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.5 }, "n": 20, "target_z": 1.50712890886636, "target_raw": 1.7854120075702666, "ce": 6.187026929855347, "genuineness": 4.210490441322326, "identity": 0.5163091450929642, "wer": 0.0029411764705882353, "valid_fraction": 1, "identity_delta": -0.059725262224674225, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.25 }, "n": 20, "target_z": 1.4601562550448786, "target_raw": 1.744655930995941, "ce": 6.219591879844666, "genuineness": 4.248146653175354, "identity": 0.512194899469614, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.06383950784802436, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.5 }, "n": 20, "target_z": 1.3451171998706861, "target_raw": 1.6448416739702225, "ce": 6.174318623542786, "genuineness": 4.16122350692749, "identity": 0.49166739657521247, "wer": 0.003125, "valid_fraction": 1, "identity_delta": -0.08436701074242592, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.25 }, "n": 20, "target_z": 1.2878906255903582, "target_raw": 1.5951887279748918, "ce": 6.206883597373962, "genuineness": 4.205783402919769, "identity": 0.5232339926064015, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.052800414711236955, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.0 }, "n": 20, "target_z": 1.1681640702014902, "target_raw": 1.4913073360919953, "ce": 6.211649203300476, "genuineness": 4.251441550254822, "identity": 0.5025700159370899, "wer": 0.003125, "valid_fraction": 1, "identity_delta": -0.07346439138054847, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" } ], "development_standard": [ { "scale": 0.0, "n": 20, "target_z": 0.2380493190075155, "target_raw": 0.68428825289011, "ce": 6.1719358444213865, "genuineness": 4.3391491889953615, "identity": 0.5760344073176384, "wer": 0.0029411764705882353, "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": 0.1337158207116626, "target_raw": 0.5937627300620079, "ce": 6.206486487388611, "genuineness": 4.3215763688087465, "identity": 0.5879116207361221, "wer": 0.0029411764705882353, "valid_fraction": 1, "identity_delta": 0.011877213418483735, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "scale": 0.75, "n": 20, "target_z": 0.16088866750769157, "target_raw": 0.6173393972218036, "ce": 6.162603235244751, "genuineness": 4.327538514137268, "identity": 0.6194714933633805, "wer": 0.005263157894736842, "valid_fraction": 1, "identity_delta": 0.043437086045742035, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "scale": 1.0, "n": 20, "target_z": 0.22019044292024328, "target_raw": 0.6687929026782513, "ce": 6.182261323928833, "genuineness": 4.359232568740845, "identity": 0.5871582925319672, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.011123885214328767, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" } ] }, "heldout": { "standard": { "n": 50, "target_z": 0.24352050843170517, "target_raw": 0.6890353599190712, "ce": 6.229281940460205, "genuineness": 4.392244567871094, "identity": 0.5804609605669975, "wer": 0.00658008658008658, "valid_fraction": 1, "identity_delta": 0.0, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" }, "manual": { "n": 50, "target_z": 1.3007788049083724, "target_raw": 1.60637122631073, "ce": 6.281227035522461, "genuineness": 4.314923686981201, "identity": 0.529170643389225, "wer": 0.01662714097496706, "valid_fraction": 0.98, "identity_delta": -0.05129031717777252, "identity_pairs": 50, "gates_pass": false, "gate_scope": "heldout_50_reference_pairs" }, "adapter": { "n": 50, "target_z": 1.594843747016008, "target_raw": 1.861518260240555, "ce": 6.241195955276489, "genuineness": 4.2461383295059205, "identity": 0.5557417982816696, "wer": 0.013120647468473554, "valid_fraction": 1, "identity_delta": -0.02471916228532791, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" }, "matched_no_adapter": { "n": 50, "target_z": 1.6413671687856473, "target_raw": 1.9018845582008361, "ce": 6.252792282104492, "genuineness": 4.249150795936584, "identity": 0.5354432153701782, "wer": 0.011110979028599165, "valid_fraction": 1, "identity_delta": -0.04501774519681931, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" } }, "adapter_vs_matched_cfg": { "n": 50, "delta_z": -0.04652342176963932, "ci95_z": [ -0.08070311404080635, -0.023671855475246636 ], "language_deltas": { "en": -0.11113279240098912, "de": -0.03808593924423995, "fr": -0.03203125375682443, "nl": -0.036914016103218004, "es": -0.014453107342925075 }, "languages_improved": 0, "clear_gain": false, "delta_ce": -0.011596326828002929, "delta_genuineness": -0.0030124664306640627, "delta_wer": 0.002009668439874389, "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": 0.2940649421076357, "ci95_z": [ 0.1692968818374205, 0.41883300237785087 ], "language_deltas": { "en": 0.16347656998681448, "de": 0.48087159976044247, "fr": 0.27734373980290505, "nl": 0.12109376470528428, "es": 0.42753903628273215 }, "languages_improved": 5, "clear_gain": true, "delta_ce": -0.04003108024597168, "delta_genuineness": -0.06878535747528076, "delta_wer": -0.0035064935064935067, "note": "Exploratory language-cluster bootstrap; five voices, one fixed reference voice per language. No familywise claim across72targets." }, "manual_vs_standard": { "n": 50, "delta_z": 1.0572582964766672, "ci95_z": [ 0.9844262605172194, 1.1085058538108747 ], "language_deltas": { "en": 1.1017578125805034, "de": 0.9226684262974071, "fr": 1.1126465084253852, "nl": 1.1077392198115499, "es": 1.0414795152684901 }, "languages_improved": 5, "clear_gain": true, "delta_ce": 0.05194509506225586, "delta_genuineness": -0.07732088088989258, "delta_wer": 0.010047054394880482, "note": "Exploratory language-cluster bootstrap; five voices, one fixed reference voice per language. No familywise claim across72targets." }, "route": { "adapter": false, "scale": 0.0, "cfg": 1.0, "reason": "No new configuration passes the held-out gates; retain standard fallback and inspect audio", "fallback_standard": true }, "reference_only": true, "updated": 1793025012.9854498 }, "rows": [ { "id": "emo_Amusement-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-0", "key": "0042d901c1b86e97d0092293ccd447428b5c1b86f9a6e5bcc99861242b8d1838", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "5f2f4e599a7b4b12f589dacc9a8d68978e6989ce13483d3d0d1ede7ae141fd43", "generation_seconds_batch": 25.272795883007348, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8912354707717896, "target_z": 0.4765624645785123, "ce": 6.022613525390625, "genuineness": 4.293961524963379, "identity": 0.6967979669570923, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/0042d901c1b86e97d0092293ccd447428b5c1b86f9a6e5bcc99861242b8d1838.mp3" }, { "id": "emo_Amusement-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-0", "key": "0077c80a65749d5670c5fed266c2bf42b91297146069d2ee4a5803ad9daf8954", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "9438e6b328f5c5be4a1c60cdbd12c23ed970a4baf072c58fddc5ed8a8ea77d59", "generation_seconds_batch": 24.404853226966225, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8876835107803345, "target_z": 1.6250000171740546, "ce": 5.927301406860352, "genuineness": 3.653805732727051, "identity": 0.40171849727630615, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás lista para tu casa.", "wer": 0.26666666666666666, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/0077c80a65749d5670c5fed266c2bf42b91297146069d2ee4a5803ad9daf8954.mp3" }, { "id": "emo_Amusement-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-0", "key": "00de59aaf76a76b7a7c2a3c9cec4930f29e9315cb05274e7a9f823454ca3054c", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The door is still open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "2f28be643de4e7743262e931e8efd4bf3b39e187bde8f953d025b36c123cb356", "generation_seconds_batch": 23.01595906703733, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8131194114685059, "target_z": 1.539062559035813, "ce": 6.221180438995361, "genuineness": 4.137060642242432, "identity": 0.21872510015964508, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/00de59aaf76a76b7a7c2a3c9cec4930f29e9315cb05274e7a9f823454ca3054c.mp3" }, { "id": "emo_Amusement-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-1", "key": "01453fba61a54d064bfe5fce3641b43e6042c6820560bf8f72ce1d0f5316c0f9", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "da84c35df75e71ab900d693847f76d1f44435d507b6cc2fb40e684dcda417bf5", "generation_seconds_batch": 19.25713780906517, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9825832843780518, "target_z": 1.7343749763856748, "ce": 5.911416053771973, "genuineness": 4.21237325668335, "identity": 0.5056922435760498, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/01453fba61a54d064bfe5fce3641b43e6042c6820560bf8f72ce1d0f5316c0f9.mp3" }, { "id": "emo_Amusement-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-0", "key": "016b11d26cf602ac8c4f1d83eac422db0a9abd278199b6814131857ce757a347", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "26151f2b10fc370c9c2cb756c2ad79bb778bd9b4c89f6dcb2ba446b0798dea0f", "generation_seconds_batch": 23.176861499086954, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.32167387008667, "target_z": 0.9726561915008763, "ce": 5.95112943649292, "genuineness": 3.7918784618377686, "identity": 0.48852765560150146, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/016b11d26cf602ac8c4f1d83eac422db0a9abd278199b6814131857ce757a347.mp3" }, { "id": "emo_Amusement-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-0", "key": "01947fe8fc9c92eb570f51743b08cce919ef506e76df007f671eff0c26035a15", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "4087866486339058e77a81010e43aa7ff99ce4837cdbc7211072399457735105", "generation_seconds_batch": 24.617716255015694, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8946247696876526, "target_z": 0.4804687376561482, "ce": 6.157639026641846, "genuineness": 4.231201171875, "identity": 0.6487361192703247, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/01947fe8fc9c92eb570f51743b08cce919ef506e76df007f671eff0c26035a15.mp3" }, { "id": "emo_Amusement-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-1", "key": "01bc54a432d3d182ef84d274529e75bfe0d7e46ef24f12186b30196089690d2a", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "b2dd097ad2bde0465e8758acb8d8cd2e3c85560ee4d76bea6cffabf12c7a9419", "generation_seconds_batch": 23.485434069065377, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0535953044891357, "target_z": 2.968749849727022, "ce": 6.165581703186035, "genuineness": 4.15588903427124, "identity": 0.6176573634147644, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. We've regarded ensemble what it contiens.", "wer": 0.3157894736842105, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/01bc54a432d3d182ef84d274529e75bfe0d7e46ef24f12186b30196089690d2a.mp3" }, { "id": "emo_Amusement-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-0", "key": "01d47bb3daca043e856a2be8175c9a06c1c47e5cba995c2679605f337b66f4de", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b7a18d436e98bb5b3b2e9c51691fabe0b535ba681b746783ea725724cb206c15", "generation_seconds_batch": 24.439315010909922, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.009697437286377, "target_z": 1.765624886221888, "ce": 6.38797664642334, "genuineness": 4.268857479095459, "identity": 0.5396714210510254, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/01d47bb3daca043e856a2be8175c9a06c1c47e5cba995c2679605f337b66f4de.mp3" }, { "id": "emo_Amusement-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-1", "key": "01dfcdc2d405f30cfed6394aa77f9e2ddebb204b5f60ad177d4e593c68948e5f", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "dd6aa38cccea149f88ac3f12b12d0b493263ee6c8a0901528cd44ec71c66c470", "generation_seconds_batch": 21.94911443197634, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4028539657592773, "target_z": 2.218750090163787, "ce": 6.141753673553467, "genuineness": 4.306513786315918, "identity": 0.625421404838562, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/01dfcdc2d405f30cfed6394aa77f9e2ddebb204b5f60ad177d4e593c68948e5f.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_Amusement", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": "eb77e4bc8d51d69c70a9861badf80582d9317c7aa5c6d360845642ddaea93f8e", "generation_seconds_batch": 18.116780833923258, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5158728361129761, "target_z": 0.043945280164475235, "ce": 6.006728172302246, "genuineness": 4.18099308013916, "identity": 0.506119966506958, "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_Amusement/01f5d5f22d9b51f4e674eec92be80d0710e62f5704093e3409bc811236eec3e5.mp3" }, { "id": "emo_Amusement-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-0", "key": "022405fbb2364022d2e9d7ffe517b72da3177e9dd5f075022909377898f37e82", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "b03e703143f5e47475514085cdf245822f3f81ab520c02eb60d062f6ea40ca97", "generation_seconds_batch": 17.867182562011294, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.206275701522827, "target_z": 1.9921874881928374, "ce": 5.816103935241699, "genuineness": 3.660081624984741, "identity": 0.4446452856063843, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre las sillas. Dime cuándo estás listo.", "wer": 0.13333333333333333, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/022405fbb2364022d2e9d7ffe517b72da3177e9dd5f075022909377898f37e82.mp3" }, { "id": "emo_Amusement-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-1", "key": "026b4784e67a3e78cc45f8383ed17e51036a0802573e3c73dc21281c232dc93c", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "58d99781058521739da579fde8d6829bc324d06bb8ec2e757fd188efe929044b", "generation_seconds_batch": 21.90396010200493, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4674129486083984, "target_z": 1.1406250407883798, "ce": 6.260893821716309, "genuineness": 4.394378662109375, "identity": 0.5551141500473022, "hypothesis": "J'ai trouvé la 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_Amusement/026b4784e67a3e78cc45f8383ed17e51036a0802573e3c73dc21281c232dc93c.mp3" }, { "id": "emo_Amusement-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-1", "key": "02f69b39b18497ad2b9cb037283fedd716d2d01e67e4f499b359cfa29fd2bba6", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I found the little box.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It was beside the old window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "10debc278a72d6d53d459e7be28ed93c6135857a861e81682bd827636ec46858", "generation_seconds_batch": 24.450061863986775, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.206275701522827, "target_z": 1.9921874881928374, "ce": 6.23706579208374, "genuineness": 4.030367851257324, "identity": 0.24962657690048218, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/02f69b39b18497ad2b9cb037283fedd716d2d01e67e4f499b359cfa29fd2bba6.mp3" }, { "id": "emo_Amusement-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-1", "key": "030b1a7bcc4ab3e342e303a5a3799a69eb11fe678e605726c9c8f6143153a537", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "a4c76fc69a5ff7b9e0bcd768cebd495f8350ced77b84f9cfe2b1184637895b1d", "generation_seconds_batch": 16.57659907999914, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.741781711578369, "target_z": 2.609374924863511, "ce": 6.308549880981445, "genuineness": 4.293961524963379, "identity": 0.5472155809402466, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/030b1a7bcc4ab3e342e303a5a3799a69eb11fe678e605726c9c8f6143153a537.mp3" }, { "id": "emo_Amusement-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-1", "key": "037017dfc096ac0e6637470f41e4f87dfb803c3ff0d3e56060dd8c808ce70de4", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I found the little box.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It was beside the old window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "872cbac20b4db4466915464a247e94c943ca1aaed908674a24d982911bed40c6", "generation_seconds_batch": 21.45707138394937, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.47063946723938, "target_z": 2.296875002146757, "ce": 6.23706579208374, "genuineness": 4.300237655639648, "identity": 0.3155897855758667, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/037017dfc096ac0e6637470f41e4f87dfb803c3ff0d3e56060dd8c808ce70de4.mp3" }, { "id": "emo_Amusement-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-0", "key": "03ad47df7ef6462b5cd899f159e87ff673fa340a35a6ba779ada7f68f801b945", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "b40f7e95d2135d65c84b32020f6aba3844003b9e3af6d03119182c6d32cc81f3", "generation_seconds_batch": 23.331489142030478, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1520471572875977, "target_z": 1.9296873937355368, "ce": 6.1894097328186035, "genuineness": 4.281409740447998, "identity": 0.6235172152519226, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/03ad47df7ef6462b5cd899f159e87ff673fa340a35a6ba779ada7f68f801b945.mp3" }, { "id": "emo_Amusement-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-1", "key": "03c6bf3214a3fa75e52fef25b58df6629af841afd820a06f989fe8351a414ff1", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "58f49abd8c39f73efefd0a02a4b8904c4ca8dd2c9035a0b01241cf2b02454a91", "generation_seconds_batch": 24.693575448007323, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1384902000427246, "target_z": 1.9140625762098675, "ce": 6.157639026641846, "genuineness": 4.174716949462891, "identity": 0.550186276435852, "hypothesis": "Ik 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_Amusement/03c6bf3214a3fa75e52fef25b58df6629af841afd820a06f989fe8351a414ff1.mp3" }, { "id": "emo_Amusement-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-1", "key": "040842ceb4fc636734bc40f9e86caeb925e2b0ffccfbe5411cf6d4e07cd1cd14", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "30b8633f0c9e803e51aaeab96e4b8a9ea9366464e32285f8fbaf9e04d951e1a0", "generation_seconds_batch": 25.116695114062168, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.206275701522827, "target_z": 1.9921874881928374, "ce": 6.09409761428833, "genuineness": 4.080576419830322, "identity": 0.7155054807662964, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana, vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/040842ceb4fc636734bc40f9e86caeb925e2b0ffccfbe5411cf6d4e07cd1cd14.mp3" }, { "id": "emo_Amusement-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-1", "key": "042da250c3fc6797da59995c03facd16f5a7d1a6a80183a3534629db9f9019a0", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "9cc4b9abe9a54f23fb29fa81db9c282df4960e3c8462c946b5146784649be5d7", "generation_seconds_batch": 20.328051723889075, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3079540729522705, "target_z": 2.1093749935597295, "ce": 6.173524379730225, "genuineness": 4.168440818786621, "identity": 0.5986601114273071, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/042da250c3fc6797da59995c03facd16f5a7d1a6a80183a3534629db9f9019a0.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": "04800e04cf3a958a3e3111729c4a7b28dcbbca0efa62c6b54e98ca449adcaa48", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7aec45204c215e8e81d214c25914d8cfdb6c62939dccb452aaea9332092d6cc8", "generation_seconds_batch": 16.80185003299266, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4028539657592773, "target_z": 2.218750090163787, "ce": 6.372091293334961, "genuineness": 4.432034492492676, "identity": 0.4816092550754547, "hypothesis": "De sleutels liggen op de keukentafel. Ik keek in de la en daarna naast de draam. Neem ze mee als je weggaat?", "wer": 0.09090909090909091, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/04800e04cf3a958a3e3111729c4a7b28dcbbca0efa62c6b54e98ca449adcaa48.mp3" }, { "id": "emo_Amusement-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-0", "key": "04ee704ca184086abd965154b3332272b3041707a562da3be62c1267dcbd2775", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "3b646ae3550c446bdcb0d75a93f9f67ec8189d7b0b73529711e317c3dad58697", "generation_seconds_batch": 24.61685392598156, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2708346843719482, "target_z": 0.9140624388174303, "ce": 6.157639026641846, "genuineness": 4.406930446624756, "identity": 0.7462451457977295, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/04ee704ca184086abd965154b3332272b3041707a562da3be62c1267dcbd2775.mp3" }, { "id": "emo_Amusement-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-0", "key": "0500e3d6d3c3132eb8b5ca797795a6f60cfd160f42e63acc4d1106b7bfdab737", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "26a8e14b0f02ed2f0519fe21e3912ddee88953208e554fd03a151909e99bdd3d", "generation_seconds_batch": 25.467357915942557, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7553389072418213, "target_z": 2.6250000171740546, "ce": 6.2767791748046875, "genuineness": 4.13078498840332, "identity": 0.39974695444107056, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/0500e3d6d3c3132eb8b5ca797795a6f60cfd160f42e63acc4d1106b7bfdab737.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_Amusement", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": "dabb06b3347aaebd1437823d6fd6988fdb6f590b6cf0f49356ee26a253a8ab3c", "generation_seconds_batch": 17.359042542986572, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5148628950119019, "target_z": 1.1953125890904084, "ce": 6.356205940246582, "genuineness": 4.645420074462891, "identity": 0.7222620248794556, "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_Amusement/059867605942d1f4c46c2c44d936e08b7fbe89dd4feef4c05500a7ed426c27a3.mp3" }, { "id": "emo_Amusement-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-0", "key": "06083b03e8fe27ce65875f4f5d8ff8e72dfca1e028e40ebbbbf105f6d2c9553c", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "392d4d340487a82863c21194f59eb1841a4fd2ca0f789e3f0d6aa5a71dd5e4f5", "generation_seconds_batch": 25.37163722398691, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8909099102020264, "target_z": 2.7812498411399944, "ce": 6.268836498260498, "genuineness": 4.18099308013916, "identity": 0.30895233154296875, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/06083b03e8fe27ce65875f4f5d8ff8e72dfca1e028e40ebbbbf105f6d2c9553c.mp3" }, { "id": "emo_Amusement-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-0", "key": "0683641932c606c15aa5c91a4e420ec1c79a59b3839ec35175727641aaae85be", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "9c347baf13cbe0cdbd426fb59d960ef582b1e2b02abf4dffd62a7f6652669aa8", "generation_seconds_batch": 20.81152436695993, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9044671058654785, "target_z": 2.796874933450538, "ce": 5.796247482299805, "genuineness": 3.747946262359619, "identity": 0.6344552636146545, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/0683641932c606c15aa5c91a4e420ec1c79a59b3839ec35175727641aaae85be.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": "07165e6fffe9d57a1c34670bc92ad8650cfbf34a963ec5c212d7b71690ccdf96", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5b764997cb5624b713a804f7231b71f81244358fa43a4a32c4991db76f473b2a", "generation_seconds_batch": 17.499346739961766, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9963032007217407, "target_z": 0.5976563117192589, "ce": 6.062326908111572, "genuineness": 4.482243061065674, "identity": 0.7407773733139038, "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_Amusement/07165e6fffe9d57a1c34670bc92ad8650cfbf34a963ec5c212d7b71690ccdf96.mp3" }, { "id": "emo_Amusement-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-0", "key": "07a8c2409b08f00a50015569a317d6030cded8af41a3b621b42fc30faee23e46", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The door is still open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "79e53a196e97b612d8865184305e43cfb9541c981d101a3ea8ece56a93f8226b", "generation_seconds_batch": 23.659133124980144, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.602984070777893, "target_z": 1.2968750021467568, "ce": 6.157639026641846, "genuineness": 3.9425034523010254, "identity": 0.49976396560668945, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/07a8c2409b08f00a50015569a317d6030cded8af41a3b621b42fc30faee23e46.mp3" }, { "id": "emo_Amusement-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-0", "key": "086f145d3cc3437923edc6dcbc544c23cd6a5226e781522643d6caff111324d5", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The door is still open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "46307c33914f34425d5c25368db3f2d04453803173486349ad07cbfc41d6441b", "generation_seconds_batch": 24.52233986801002, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.145431399345398, "target_z": 0.7695312279957425, "ce": 6.086154937744141, "genuineness": 4.13078498840332, "identity": 0.3720153570175171, "hypothesis": "The 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_Amusement/086f145d3cc3437923edc6dcbc544c23cd6a5226e781522643d6caff111324d5.mp3" }, { "id": "emo_Amusement-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-0", "key": "090785bed729aa822687e78f0db716f3e731d45712aa824d42b0db62ae6002f9", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De deur staat nog open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "b6499e57e678af35098f2948af54abe27ed8abb7c14746593c3c0ca071ee2266", "generation_seconds_batch": 21.78505861898884, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5248677730560303, "target_z": 2.3593748218191832, "ce": 6.070269584655762, "genuineness": 4.21237325668335, "identity": 0.46712207794189453, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/090785bed729aa822687e78f0db716f3e731d45712aa824d42b0db62ae6002f9.mp3" }, { "id": "emo_Amusement-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-1", "key": "0948404faa6482079aa1595f7482bacd44adf3d3c2222479e8b5608ef10dd05e", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1fbbf40b4be2a720fa5905ec6d638fa472c9b53f9f2af87041f3431f28a1f71e", "generation_seconds_batch": 21.153170068049803, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1859400272369385, "target_z": 1.968749987119459, "ce": 6.197352409362793, "genuineness": 3.8295347690582275, "identity": 0.3945986032485962, "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_Amusement/0948404faa6482079aa1595f7482bacd44adf3d3c2222479e8b5608ef10dd05e.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": "094aca8090e2e47cd8b2efa95e3ee63bd40cf856c8b0a528104e6d2b06042b6d", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "655b77b1f8edfa21769379f8c9f8e2f9b95cf8d0441fe30112507e0ae4907701", "generation_seconds_batch": 19.667723782011308, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.023417353630066, "target_z": 0.628906221555472, "ce": 6.324435234069824, "genuineness": 4.149612903594971, "identity": 0.13540509343147278, "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_Amusement/094aca8090e2e47cd8b2efa95e3ee63bd40cf856c8b0a528104e6d2b06042b6d.mp3" }, { "id": "emo_Amusement-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-1", "key": "09ea1c7cc453eadf27839379d5d9e53b3c539232fe48fb01362efe3916089931", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "70758dee9631a2f48f20f33ec0b8b213d6a213289a790caade0b503e82d70bd7", "generation_seconds_batch": 21.266844974947162, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.104597330093384, "target_z": 1.8749999828259454, "ce": 5.927301406860352, "genuineness": 3.9173994064331055, "identity": 0.5773261785507202, "hypothesis": "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_Amusement/09ea1c7cc453eadf27839379d5d9e53b3c539232fe48fb01362efe3916089931.mp3" }, { "id": "emo_Amusement-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-1", "key": "0a0ce910da95beba847581b1cc9b95e8e68136dcaa6b9dfffd85894afcbdabf9", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "704b8bff04c5adc80431a02e4cb56df5427e3bc0ed485c203f0993ec3ccf52e5", "generation_seconds_batch": 24.344563807942905, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8605692386627197, "target_z": 1.5937499699454043, "ce": 6.443574905395508, "genuineness": 4.017816066741943, "identity": 0.5101522207260132, "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_Amusement/0a0ce910da95beba847581b1cc9b95e8e68136dcaa6b9dfffd85894afcbdabf9.mp3" }, { "id": "emo_Amusement-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-1", "key": "0a20de67a2a9e6e22c543dd7efdedb884267c8be019281c814b72190d72e2fdc", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "23abd04c4f38991d00ca33bc25bbaf584c8f093d1bb82aa01996c1fbca74f426", "generation_seconds_batch": 24.705629062023945, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6911053657531738, "target_z": 1.3984375525955424, "ce": 6.395919322967529, "genuineness": 4.174716949462891, "identity": 0.529206395149231, "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_Amusement/0a20de67a2a9e6e22c543dd7efdedb884267c8be019281c814b72190d72e2fdc.mp3" }, { "id": "emo_Amusement-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-1", "key": "0a34cab5aca8a736edb4a73bf185b3299d9189684145d6e78e14034afdabb7fc", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "abbcc9c83006d15de9670e1fae9d921c449c4700e87e91b08dc08eeeb4d0c7b8", "generation_seconds_batch": 24.36850266600959, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0268067121505737, "target_z": 0.6328125633293266, "ce": 6.062326908111572, "genuineness": 4.15588903427124, "identity": 0.633398175239563, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/0a34cab5aca8a736edb4a73bf185b3299d9189684145d6e78e14034afdabb7fc.mp3" }, { "id": "emo_Amusement-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-0", "key": "0b5adfdce1ca3be66a57cd99d9fa9213e57463c76716f3147eeb3f8bc60d8497", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De deur staat nog open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "1c03ad3b1283ade3ec68e89c31e6dbb5e450d6ba599b28298e0ced2162d07559", "generation_seconds_batch": 24.603451007045805, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5013056993484497, "target_z": 1.1796874967798647, "ce": 6.2767791748046875, "genuineness": 4.375550270080566, "identity": 0.59034663438797, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/0b5adfdce1ca3be66a57cd99d9fa9213e57463c76716f3147eeb3f8bc60d8497.mp3" }, { "id": "emo_Amusement-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-0", "key": "0bcc1cdc54861b78bdb1b24087565ed608286a6e74a70cb5d86c8d016ca6972e", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "564cc36a093e11cc5eecb0570cd1d25a319125a210db4943de9d298b05bbd467", "generation_seconds_batch": 22.84430093097035, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.26744544506073, "target_z": 0.910156234436013, "ce": 6.268836498260498, "genuineness": 4.362998008728027, "identity": 0.6703295111656189, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/0bcc1cdc54861b78bdb1b24087565ed608286a6e74a70cb5d86c8d016ca6972e.mp3" }, { "id": "emo_Amusement-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-0", "key": "0c44b79ad1433d2d1d1883f42f06e3c1914efa8df6423c40dccf62bee49c92af", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "7ee53c65e3b83ac28462bfe9350b09cbee7542e355265835b6dc6a6e12f7cba0", "generation_seconds_batch": 24.22056260309182, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6843267679214478, "target_z": 1.3906250064402705, "ce": 5.831989288330078, "genuineness": 3.7542223930358887, "identity": 0.5874015688896179, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/0c44b79ad1433d2d1d1883f42f06e3c1914efa8df6423c40dccf62bee49c92af.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": "0c70eae6215cac4e29d97c36d2750da00f7e636796908126d763f462cf1712fe", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "d67bed0a4cde61ffccc65c4c6ab94b50ff55e0375e561055745bc7a3e53f5169", "generation_seconds_batch": 22.33729331404902, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6468818187713623, "target_z": 2.4999998282594533, "ce": 6.173524379730225, "genuineness": 4.356721878051758, "identity": 0.563186764717102, "hypothesis": "De sleutels liggen op de keukentafel. Ik keek in de la en daarna, naast het raam, neem ze mee als je weggaat.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/0c70eae6215cac4e29d97c36d2750da00f7e636796908126d763f462cf1712fe.mp3" }, { "id": "emo_Amusement-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-0", "key": "0c8faa31944a424dad3321ab68b27eb13fe4073061dbc9427a5d4088bf01cbcc", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "66d762f4d9463d2dd630f70d765ae49f631475079f62139d564859515b86e810", "generation_seconds_batch": 22.548589071957394, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4164109230041504, "target_z": 2.2343749076894563, "ce": 6.181467056274414, "genuineness": 4.193545341491699, "identity": 0.5268703103065491, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/0c8faa31944a424dad3321ab68b27eb13fe4073061dbc9427a5d4088bf01cbcc.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_Amusement", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": "9fd987ec8d4fd148cb586c191c4d38581ae3e1972ca490c9ba4bf16bc0591d24", "generation_seconds_batch": 17.39465751789976, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6438181400299072, "target_z": 0.19140624731655395, "ce": 6.252951145172119, "genuineness": 4.394378662109375, "identity": 0.6265182495117188, "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_Amusement/0cb70e86df8754d3bba44fe7f798aac7d0ffe2ca68fc75b92ff1a1ed29986ba7.mp3" }, { "id": "emo_Amusement-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-1", "key": "0cca024e8f2cb150f7226a5bb099e773ffcdb8894f1d6036272dfef9cbc3d732", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "21e1dd568ff4788caa5c1414a75bb39912fa6ad2ae84e3b8aa6cae5d004735df", "generation_seconds_batch": 22.070913912029937, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2808399200439453, "target_z": 2.0781250837235166, "ce": 6.157639026641846, "genuineness": 4.024092197418213, "identity": 0.7907850742340088, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/0cca024e8f2cb150f7226a5bb099e773ffcdb8894f1d6036272dfef9cbc3d732.mp3" }, { "id": "emo_Amusement-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-1", "key": "0cf57b256b4868bea3cfc558bb50a41676c36422de6a615cc4c8fc6f65de1ecf", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "d738db035643eae5e4412c9776b90b4217d09b729fd7b4263cb2eb34db536916", "generation_seconds_batch": 22.335996659006923, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5962055921554565, "target_z": 1.2890625933839222, "ce": 6.086154937744141, "genuineness": 4.545003414154053, "identity": 0.7143062353134155, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/0cf57b256b4868bea3cfc558bb50a41676c36422de6a615cc4c8fc6f65de1ecf.mp3" }, { "id": "emo_Amusement-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-1", "key": "0d45c0156e1eaf6956ad93acb36c26b76e3983c00219967c8855ed27634d36f6", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I found the little box.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It was beside the old window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ed7d64c0bc7e54a57f5e3cfc6f7d6c88c04c3fd114a4fc9dd3fffe85359001f5", "generation_seconds_batch": 18.885680835926905, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5519821643829346, "target_z": 2.3906250064402705, "ce": 5.967014789581299, "genuineness": 3.823258876800537, "identity": 0.5795507431030273, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/0d45c0156e1eaf6956ad93acb36c26b76e3983c00219967c8855ed27634d36f6.mp3" }, { "id": "emo_Amusement-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-0", "key": "0d698b042aa68e4b30a0c9e81c867f47bd189952a17bc8ff5eef832e7f63d65a", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De deur staat nog open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "f529ea54fc6c602d3d2779b15bc37a622df363b45c5a734717ecaffc0985fa7e", "generation_seconds_batch": 23.358618611004204, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.619767665863037, "target_z": 2.4687499184232404, "ce": 6.109982967376709, "genuineness": 4.193545341491699, "identity": 0.7469055652618408, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar, wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/0d698b042aa68e4b30a0c9e81c867f47bd189952a17bc8ff5eef832e7f63d65a.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": "0de1d55669925d6acbafa705493eaedba6e1a540c33ceaf76c2437392e0bb835", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The keys are on the kitchen table.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6c7d72bd684d854318484005f322b67aecb3bbc70ed6c8bbe3f48f57666e00a5", "generation_seconds_batch": 22.57794579898473, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2943968772888184, "target_z": 2.093749901249186, "ce": 6.427689552307129, "genuineness": 3.9299514293670654, "identity": 0.45689523220062256, "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_Amusement/0de1d55669925d6acbafa705493eaedba6e1a540c33ceaf76c2437392e0bb835.mp3" }, { "id": "emo_Amusement-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-1", "key": "0de70a4686b4aaab1548768874d76216320b4fcac857d9ad4b0578051c834e10", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I found the little box.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It was beside the old window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "4c8580114cf5028fa79be9a5abb1a1b3587c8f9a2c8fea356a8fa33f00180f60", "generation_seconds_batch": 25.157122698961757, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.131711483001709, "target_z": 1.9062498926621585, "ce": 6.1894097328186035, "genuineness": 4.2374773025512695, "identity": 0.4099368453025818, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/0de70a4686b4aaab1548768874d76216320b4fcac857d9ad4b0578051c834e10.mp3" }, { "id": "emo_Amusement-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-1", "key": "0deb96e24796064b366042e142c0c6c314efe047a7278ba6efddd0ff785a1ca4", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I found the little box.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It was beside the old window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "2a24c8046172b23691c5128f45a7e0efbf273840ae530f7a59b3d18b6f95ef5b", "generation_seconds_batch": 24.358915442950092, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5113108158111572, "target_z": 2.3437500042935135, "ce": 6.300607204437256, "genuineness": 4.457139015197754, "identity": 0.3291510343551636, "hypothesis": "I found the little box. It was beside the old window. We can look inside together?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/0deb96e24796064b366042e142c0c6c314efe047a7278ba6efddd0ff785a1ca4.mp3" }, { "id": "emo_Amusement-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-0", "key": "0dfe9824c31d03e84d3d0938aab8c216ff3eb205ac5a469dcc69b065421f0dbf", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De deur staat nog open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "56175af2e97844c758544b6ea73d4967a2a98bbba66f73b6a08a5e079b4c504b", "generation_seconds_batch": 21.340378936962225, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1620521545410156, "target_z": 3.0937497638567484, "ce": 5.7128496170043945, "genuineness": 4.017816066741943, "identity": 0.608686625957489, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/0dfe9824c31d03e84d3d0938aab8c216ff3eb205ac5a469dcc69b065421f0dbf.mp3" }, { "id": "emo_Amusement-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-0", "key": "0e08a0fcc8d5c8924fb4ac300a98dd85882041f1f686516b395289eb264bb847", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d08203bed0041b858c97e57d810fefa8dbb45b4ed9e1b3b1c974910147bcd7da", "generation_seconds_batch": 17.246657934971154, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8095672130584717, "target_z": 2.687499836846481, "ce": 6.165581703186035, "genuineness": 4.18099308013916, "identity": 0.5935543179512024, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/0e08a0fcc8d5c8924fb4ac300a98dd85882041f1f686516b395289eb264bb847.mp3" }, { "id": "emo_Amusement-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-0", "key": "0e5a23a70386e78ac1fb1944449dedd0dcc44530f6d45f8550f971e771162804", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2877e0475b5a69bb8cb73a59cf1cfa9dc70a7be6f92ee8b955996de5791397ac", "generation_seconds_batch": 23.802513358998112, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0435903072357178, "target_z": 1.80468747960581, "ce": 6.292664527893066, "genuineness": 4.482243061065674, "identity": 0.6626472473144531, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/0e5a23a70386e78ac1fb1944449dedd0dcc44530f6d45f8550f971e771162804.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": "0ed758cd5533a32ac89884967fbdf6f5f02dd2a103dfeab8b725e505327caa7d", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b45dcd9a2b88f9ab1981b6f4ffe57258c316486b0ce4acc1d5239ee0b618e0cb", "generation_seconds_batch": 19.123501325957477, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9758048057556152, "target_z": 1.7265625676228402, "ce": 6.070269584655762, "genuineness": 4.532451152801514, "identity": 0.5889982581138611, "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_Amusement/0ed758cd5533a32ac89884967fbdf6f5f02dd2a103dfeab8b725e505327caa7d.mp3" }, { "id": "emo_Amusement-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-0", "key": "0eedb72c71f44233ce8f9e4021014ba2a2b799548780f9c690092991ca6c9038", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The door is still open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "2545f03bd0d568d6f7b5a20f3a0bf42fc934a35c3168d81ff1c847daaa925e5e", "generation_seconds_batch": 23.659133124980144, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.901240587234497, "target_z": 1.6406249720921613, "ce": 6.1894097328186035, "genuineness": 3.6789097785949707, "identity": 0.17514289915561676, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/0eedb72c71f44233ce8f9e4021014ba2a2b799548780f9c690092991ca6c9038.mp3" }, { "id": "emo_Amusement-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-0", "key": "0f4d9bd568810d349d022bea290200f825d211047c4be3bef14a3dc312fa6bc8", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The door is still open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "1916f796499cae9af7b0ab69e685da86c215de707d52b45b466b52830403de1a", "generation_seconds_batch": 23.662918975926004, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.16560435295105, "target_z": 1.9453124860460806, "ce": 6.284721851348877, "genuineness": 3.798154592514038, "identity": 0.22789376974105835, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/0f4d9bd568810d349d022bea290200f825d211047c4be3bef14a3dc312fa6bc8.mp3" }, { "id": "emo_Amusement-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-0", "key": "0f5f45c76437474def9e7ba79deeb741db6f8999bb70531cd5f0c430514fc7e2", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "3674a6a55f681bc60eaa18b342bb0dd7a56c33955c554aa25cb6095b2f235b90", "generation_seconds_batch": 23.51359774102457, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4335200786590576, "target_z": 1.1015624474044576, "ce": 5.847874641418457, "genuineness": 3.653805732727051, "identity": 0.4015325903892517, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/0f5f45c76437474def9e7ba79deeb741db6f8999bb70531cd5f0c430514fc7e2.mp3" }, { "id": "emo_Amusement-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-1", "key": "10071d2c09aca5af01e5f31282a97e44e49d0439ea4687f1fbb8eadf07b225a1", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I found the little box.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It was beside the old window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "417d59e37a320876b9791382fb78fb5e3bfd38228f2193796a2795c069ab1b68", "generation_seconds_batch": 24.767315716017038, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0435903072357178, "target_z": 1.80468747960581, "ce": 6.41180419921875, "genuineness": 4.256305694580078, "identity": 0.426653116941452, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/10071d2c09aca5af01e5f31282a97e44e49d0439ea4687f1fbb8eadf07b225a1.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": "10085440acf4a8da85f3c1b96008af15b30e17131dab16a119b5f9b2efd7d59f", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5068b00d671fecaf6feb71e97e21479e9883fbba203ff35a360daf0700021e1e", "generation_seconds_batch": 20.770328166894615, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8131194114685059, "target_z": 1.539062559035813, "ce": 6.372091293334961, "genuineness": 4.168440818786621, "identity": 0.3762626051902771, "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_Amusement/10085440acf4a8da85f3c1b96008af15b30e17131dab16a119b5f9b2efd7d59f.mp3" }, { "id": "emo_Amusement-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-1", "key": "104d1ad88aa539bcf0c720d62300ea29fbb6b017bb94a29c9208faeb67772d5a", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "6a3e347801ac933a93232f616e77d26c8eb85b39b56bb1c5ce100a653fc04c53", "generation_seconds_batch": 24.250329770962708, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.118154525756836, "target_z": 1.890625075136489, "ce": 6.086154937744141, "genuineness": 4.319066047668457, "identity": 0.45724111795425415, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/104d1ad88aa539bcf0c720d62300ea29fbb6b017bb94a29c9208faeb67772d5a.mp3" }, { "id": "emo_Amusement-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-1", "key": "106f040b4781fb35930ba15cfa5514e32d8c05c09adc90e8cf05ed39b09b22e9", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "688538a4d232193b91a081f7c7eb9a3a206941662c8d90f6a2e88257280a0b99", "generation_seconds_batch": 24.414886599057354, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.985809803009033, "target_z": 2.890624937744052, "ce": 6.133810997009277, "genuineness": 4.243753433227539, "identity": 0.5950558185577393, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana, vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/106f040b4781fb35930ba15cfa5514e32d8c05c09adc90e8cf05ed39b09b22e9.mp3" }, { "id": "emo_Amusement-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-0", "key": "10b0991b013ed4522129253fea402373508cadfbd2b807ea2463670c5bce38f6", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "1e0348f73a1b2db3b4831695102227f746fc16816b27d57f933139a74ea2b891", "generation_seconds_batch": 20.42649314389564, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.023254632949829, "target_z": 1.7812499785324316, "ce": 5.879645347595215, "genuineness": 3.735394239425659, "identity": 0.6221648454666138, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/10b0991b013ed4522129253fea402373508cadfbd2b807ea2463670c5bce38f6.mp3" }, { "id": "emo_Amusement-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-1", "key": "10d83c9f17ffd2711d3041f9519d20356f0e1da9fd100b201c0ab45ee440919e", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5fecf30fa6bba401821e6f77eacf8679535a2d2133b2eb89b4d4ec71192bee80", "generation_seconds_batch": 18.1234682550421, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1249330043792725, "target_z": 1.8984374838993239, "ce": 6.41180419921875, "genuineness": 3.6851859092712402, "identity": 0.5701602697372437, "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_Amusement/10d83c9f17ffd2711d3041f9519d20356f0e1da9fd100b201c0ab45ee440919e.mp3" }, { "id": "emo_Amusement-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-1", "key": "10ee62a75169ce36865719be83b4af4739019451f161412af5eda82457b1618f", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b6a9c929769c57f3278e52ef269b3184f1b23c9cf153b93f4bca8a3288e88dba", "generation_seconds_batch": 21.41946652799379, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8876835107803345, "target_z": 1.6250000171740546, "ce": 6.213237762451172, "genuineness": 4.042920112609863, "identity": 0.6678124666213989, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/10ee62a75169ce36865719be83b4af4739019451f161412af5eda82457b1618f.mp3" }, { "id": "emo_Amusement-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-0", "key": "11191fd883f1f85ca61dde3241c65960fa241411b8489c872b93528c3b1f0e0d", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The door is still open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "202109b142914f0a927d1294d5d2ee39c93f4de7eecaa3445d395ca98435b898", "generation_seconds_batch": 24.34233834699262, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9554691314697266, "target_z": 1.7031250665494617, "ce": 6.213237762451172, "genuineness": 3.8044304847717285, "identity": 0.42654871940612793, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/11191fd883f1f85ca61dde3241c65960fa241411b8489c872b93528c3b1f0e0d.mp3" }, { "id": "emo_Amusement-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-1", "key": "113fd329cea00ffb9bb1f2a7033c077b1638351d7380e30dee34ca7f5f84ede0", "bucket": "emo_Amusement", "phase": "wording", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I found the little box.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It was beside the old window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "f19efc48d2fabda0f5ee9f81e1bdf4d960f92763b424aba27f1f3c1bc0f0334c", "generation_seconds_batch": 18.075810362934135, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6911053657531738, "target_z": 1.3984375525955424, "ce": 6.395919322967529, "genuineness": 4.432034492492676, "identity": 0.4444964826107025, "hypothesis": "I found the little box. It was beside the old window. We can look inside together", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/113fd329cea00ffb9bb1f2a7033c077b1638351d7380e30dee34ca7f5f84ede0.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": "1148363bc08bc1ac60ae25ff77a8769afa4daddc2033ec21a49cdbc3afc06baf", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6110b8a7437c06516dbc18f08df694a2d67895c1e2790ef4c1a07bee80ad1fd1", "generation_seconds_batch": 17.017023405991495, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9827460050582886, "target_z": 0.5820312194087152, "ce": 6.23706579208374, "genuineness": 4.400654315948486, "identity": 0.5890613794326782, "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_Amusement/1148363bc08bc1ac60ae25ff77a8769afa4daddc2033ec21a49cdbc3afc06baf.mp3" }, { "id": "emo_Amusement-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-0", "key": "123570e1f483c13908d7f677e81152ce835a8ede2576e6d59bd41c619db3c6f6", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "661aef28459d8646dcddbf28fb4710588d7d6e4d872d8d36f90d648175159d71", "generation_seconds_batch": 24.04601965995971, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4470772743225098, "target_z": 1.1171875397150013, "ce": 5.9431867599487305, "genuineness": 3.7040140628814697, "identity": 0.5126725435256958, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/123570e1f483c13908d7f677e81152ce835a8ede2576e6d59bd41c619db3c6f6.mp3" }, { "id": "emo_Amusement-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-1", "key": "125a7635518b57f425d04f9d90e1e29cbfccbafb5dc9caaf1867eccd102787b0", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d77e15f790ce50419c96df2dbedd912cadb4305b3785fe6e0c99525249d7fc2a", "generation_seconds_batch": 24.859540752018802, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2943968772888184, "target_z": 2.093749901249186, "ce": 6.300607204437256, "genuineness": 3.810706615447998, "identity": 0.34944212436676025, "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_Amusement/125a7635518b57f425d04f9d90e1e29cbfccbafb5dc9caaf1867eccd102787b0.mp3" }, { "id": "emo_Amusement-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-1", "key": "129f791337cb36aa4d0138a796f0dca28d499bb457e65550b6b39f1186da4d1e", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I found the little box.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It was beside the old window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "a7c09605f11501644f0b22a8984c44136570a6878d27c4343eff73befafd5296", "generation_seconds_batch": 24.450061863986775, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6468818187713623, "target_z": 2.4999998282594533, "ce": 6.300607204437256, "genuineness": 3.8922953605651855, "identity": 0.6063260436058044, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/129f791337cb36aa4d0138a796f0dca28d499bb457e65550b6b39f1186da4d1e.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_Amusement", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "5490c41cf31b76a678765965de6f6917c5ffbe278f2f0223e824e26c35b1f22c", "generation_seconds_batch": 17.586503845988773, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1013708114624023, "target_z": 0.7187500214675683, "ce": 6.157639026641846, "genuineness": 4.507347106933594, "identity": 0.7149450182914734, "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_Amusement/12a7b850c68b1e935d69d2b179f3c0df54c4775061935760902fd9f6cbfc7541.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": "12c6f323295a44f9b5a3f738a2894f2d50e3ab158328ab5e9a20862f05d19bd5", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Someone moved the little blue chair.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "69d1eafa6d6720a2584d1277e0aa1f99524b99cc40805d2b0d07d7e17cfa6f42", "generation_seconds_batch": 16.736577088944614, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8063408136367798, "target_z": 1.531250012880541, "ce": 6.332377910614014, "genuineness": 4.162164688110352, "identity": 0.44102156162261963, "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_Amusement/12c6f323295a44f9b5a3f738a2894f2d50e3ab158328ab5e9a20862f05d19bd5.mp3" }, { "id": "emo_Amusement-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-0", "key": "12d2ece631ef3ec902d793866ccc31904f95d950479a78f8f308f07433e1e22e", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "57de9717529d5d94612a00a7a9c730bf17fa0f33421e84ee4b2c57d3bdd766e0", "generation_seconds_batch": 24.1704019960016, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3350682258605957, "target_z": 2.140624903395943, "ce": 5.863759994506836, "genuineness": 4.074300289154053, "identity": 0.5248631238937378, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/12d2ece631ef3ec902d793866ccc31904f95d950479a78f8f308f07433e1e22e.mp3" }, { "id": "emo_Amusement-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-1", "key": "130047e7134809507e3f765c89d36c5a0c1d2aa9e1ca2e6b318f61d34009b7d8", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "acdea587eb40ccc46fc364415e066bd1b04655e5931e84c1aea5ec089bd8c642", "generation_seconds_batch": 25.962647582986392, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5894269943237305, "target_z": 1.2812500472286503, "ce": 6.09409761428833, "genuineness": 4.055472373962402, "identity": 0.6943964958190918, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/130047e7134809507e3f765c89d36c5a0c1d2aa9e1ca2e6b318f61d34009b7d8.mp3" }, { "id": "emo_Amusement-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-0", "key": "1335aea98f7b10d273e4516595bc11ab7ca63bef3fb4a65a6bb24295542aee47", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The door is still open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "652a31438f7883bfe82fbf6701c4db5224a51416c7b762a4fb61c687f210ee15", "generation_seconds_batch": 22.685833358904347, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0639259815216064, "target_z": 1.8281249806791886, "ce": 6.173524379730225, "genuineness": 3.948779582977295, "identity": 0.2763255834579468, "hypothesis": "The door is still open. I put your code 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_Amusement/1335aea98f7b10d273e4516595bc11ab7ca63bef3fb4a65a6bb24295542aee47.mp3" }, { "id": "emo_Amusement-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-1", "key": "13926a6656e41417da2e15bafc46fe3d408d2ceec120f64931359a949bc75821", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "588d81f19693891b85de4716fdc261a8e7730bb7e03160472679aee9f0ecdffb", "generation_seconds_batch": 16.974856312968768, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6572126150131226, "target_z": 1.3593750966040574, "ce": 6.23706579208374, "genuineness": 4.293961524963379, "identity": 0.48408710956573486, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/13926a6656e41417da2e15bafc46fe3d408d2ceec120f64931359a949bc75821.mp3" }, { "id": "emo_Amusement-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-1", "key": "13ce992a72b398851ae27e539dc1108b167e296d7b2471aa9fb4196751de859c", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "6c912cd811efedc78490fd3ec6cbc27d9ba1265e106f1ba9f7c80464dc0b5622", "generation_seconds_batch": 22.471723788999952, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1488206386566162, "target_z": 0.7734374323771598, "ce": 6.1894097328186035, "genuineness": 4.344170093536377, "identity": 0.5624109506607056, "hypothesis": "J'ai trouvé la 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_Amusement/13ce992a72b398851ae27e539dc1108b167e296d7b2471aa9fb4196751de859c.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": "13e49c688c598cf8cb3a1f39f79f658ca5c87e25d7d2952733a97295575d29f5", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Escribí el número en el sobre.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3bb6eb943371b8d2e6d26966046b108ba707bb0706876d4f7cc44b643d800717", "generation_seconds_batch": 17.294284036033787, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8266764879226685, "target_z": 1.5546875139539194, "ce": 6.181467056274414, "genuineness": 4.344170093536377, "identity": 0.7801221609115601, "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_Amusement/13e49c688c598cf8cb3a1f39f79f658ca5c87e25d7d2952733a97295575d29f5.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": "13f26bd2a9cc8fe70c078d74ce1498bb302168ac8ece7929b84d661c1f8ba513", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e2cca333ce99057a25fa111d155a4b38c8532f71143171fe6f57c60395ebae9a", "generation_seconds_batch": 19.479360562050715, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.823124408721924, "target_z": 2.7031249291570245, "ce": 6.117925643920898, "genuineness": 4.231201171875, "identity": 0.7507504224777222, "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_Amusement/13f26bd2a9cc8fe70c078d74ce1498bb302168ac8ece7929b84d661c1f8ba513.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": "1433de39fd106e1f39ee8a64eb17fc8888cf22a29f3cee2326ba5e0952e475c9", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c3f5827fd3dec610786d335d575456a8ce199dfee2013278cc955cabb5b6a09a", "generation_seconds_batch": 20.770328166894615, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4064059257507324, "target_z": 1.0703125375682445, "ce": 6.348263263702393, "genuineness": 4.099404335021973, "identity": 0.46574866771698, "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_Amusement/1433de39fd106e1f39ee8a64eb17fc8888cf22a29f3cee2326ba5e0952e475c9.mp3" }, { "id": "emo_Amusement-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-0", "key": "14bd88bebabd18e3a711d1a5ffc9e39a0e01094e872ff11dd6eea6e6dc0b0914", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "03fc4a555704194c22925696c9a6bf8788cb982a0462c2239640f23d9ac7e3c5", "generation_seconds_batch": 22.39655245002359, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7421072721481323, "target_z": 0.3046875483020287, "ce": 6.2767791748046875, "genuineness": 4.111956596374512, "identity": 0.5075238943099976, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/14bd88bebabd18e3a711d1a5ffc9e39a0e01094e872ff11dd6eea6e6dc0b0914.mp3" }, { "id": "emo_Amusement-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-1", "key": "15213df3d86fc4a6401ef947a221445d423e72d8c151d14fccbacffa60fc09ae", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "5481588c9536674e1dbb2132e52ff33b6258b62ab93673f9dbd3bd7897b09a8f", "generation_seconds_batch": 17.696634375024587, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6504340171813965, "target_z": 1.3515625504487856, "ce": 6.149696350097656, "genuineness": 4.306513786315918, "identity": 0.7126349210739136, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/15213df3d86fc4a6401ef947a221445d423e72d8c151d14fccbacffa60fc09ae.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_Amusement", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": "50e4a54d67768c2a3a8b3f161e8036a65fa5d3948f26f9abbaaab1b0f612152f", "generation_seconds_batch": 18.065792068024166, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1422048807144165, "target_z": -0.38671873336263457, "ce": 6.213237762451172, "genuineness": 4.331617832183838, "identity": 0.5569051504135132, "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_Amusement/15585f3962d31fd159bb39a755593ab24aa0df87e4725d7772f40811258760f5.mp3" }, { "id": "emo_Amusement-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-0", "key": "15910b063d5be16029900afbda67dc833f4cb60fbcfe97bfb6c7a3ad861dac89", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The door is still open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "59af2d38ea3632d14188f5d08b5b2a45c41cb8941c0e94762ec14f48f0aa84c2", "generation_seconds_batch": 17.79855490999762, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6436554193496704, "target_z": 1.3437500042935138, "ce": 6.260893821716309, "genuineness": 3.9676074981689453, "identity": 0.4106600880622864, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/15910b063d5be16029900afbda67dc833f4cb60fbcfe97bfb6c7a3ad861dac89.mp3" }, { "id": "emo_Amusement-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-1", "key": "16917d44c5576ad549c53e1f67ce583dd6c032f040bd962dd93acbe591d20337", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "e48ce892f4b005894a27cf58bd8f720b151572848c9e6cf80177f4ef64cffb72", "generation_seconds_batch": 20.764672093908302, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.728224515914917, "target_z": 2.5937498325529673, "ce": 6.205295085906982, "genuineness": 4.055472373962402, "identity": 0.565940260887146, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/16917d44c5576ad549c53e1f67ce583dd6c032f040bd962dd93acbe591d20337.mp3" }, { "id": "emo_Amusement-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-0", "key": "171d9621cf870833b8d0f89ff7278a328fb53310058e28898643f98ce9fdcedd", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The door is still open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "6a262a5b98ccfbcb920293e1deac542c13cb8b62c6ab7d896ec6451fb5909a12", "generation_seconds_batch": 23.01595906703733, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8673478364944458, "target_z": 1.6015625161006761, "ce": 6.205295085906982, "genuineness": 3.986435890197754, "identity": 0.34701597690582275, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/171d9621cf870833b8d0f89ff7278a328fb53310058e28898643f98ce9fdcedd.mp3" }, { "id": "emo_Amusement-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-1", "key": "172c66911e74e91676dfb45a718d9ebef5cf66d9b7775897cf9e1207db136b9e", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "987da196005092fcab59a38e6bad36fb639f40b608961c2adf359db2c06ce2cc", "generation_seconds_batch": 16.794722120976076, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6468818187713623, "target_z": 2.4999998282594533, "ce": 6.133810997009277, "genuineness": 4.18099308013916, "identity": 0.45767515897750854, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/172c66911e74e91676dfb45a718d9ebef5cf66d9b7775897cf9e1207db136b9e.mp3" }, { "id": "emo_Amusement-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-0", "key": "175f14d5d65912ed5cdd7958acd2ce266e404047db182344a026d524efcc4aef", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "1df8946a9c12c26787568924852c0299dc3620c9e67d0e036a5a5d91d2bd1560", "generation_seconds_batch": 22.56086375808809, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3453989028930664, "target_z": 1.0000000343481092, "ce": 6.340320587158203, "genuineness": 4.306513786315918, "identity": 0.6616164445877075, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/175f14d5d65912ed5cdd7958acd2ce266e404047db182344a026d524efcc4aef.mp3" }, { "id": "emo_Amusement-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-1", "key": "177b78137df77f405b39a38928f15ada34eed4e819ec78d111029b170be103af", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "c429271e6ba0b296646565ee031d9c4710aa5db1b6766ae9de037e4d95dc2313", "generation_seconds_batch": 23.216642514104024, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.08070969581604, "target_z": 3.0000000343481092, "ce": 5.855817794799805, "genuineness": 4.281409740447998, "identity": 0.6410707235336304, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/177b78137df77f405b39a38928f15ada34eed4e819ec78d111029b170be103af.mp3" }, { "id": "emo_Amusement-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-1", "key": "18c7d905631ea7b6b5dab09f86d39f229ee6444c13b8c240843cbab223a119b3", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I found the little box.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It was beside the old window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "ed1f9a94519b16d7ef0cf09ff82d90360c3a66ac1fc2e167803881e2998e589e", "generation_seconds_batch": 22.595749531988986, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.118154525756836, "target_z": 1.890625075136489, "ce": 6.356205940246582, "genuineness": 4.300237655639648, "identity": 0.4019116461277008, "hypothesis": "I found the little box. It was beside the old window. We can look inside together", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/18c7d905631ea7b6b5dab09f86d39f229ee6444c13b8c240843cbab223a119b3.mp3" }, { "id": "emo_Amusement-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-0", "key": "195570edb01356e269d8f24edc2f256f2fb267a01ff556c4f802870b9a0cfc53", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "b70732c872846c93c889aba63a842b4cf0234564aaf0092b1dfed594f768da92", "generation_seconds_batch": 22.453514160006307, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5519821643829346, "target_z": 2.3906250064402705, "ce": 6.054384231567383, "genuineness": 3.923675537109375, "identity": 0.51509028673172, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/195570edb01356e269d8f24edc2f256f2fb267a01ff556c4f802870b9a0cfc53.mp3" }, { "id": "emo_Amusement-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-0", "key": "19d47b837ad0f041ba311e9a8b2e45831ab541bbf05d9df67bf82b41f7590952", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "74a920b760db84adec12abcb3bae2afaf991f965235a788414441198846bdffc", "generation_seconds_batch": 24.63210084394086, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0573102235794067, "target_z": 0.6679688149393941, "ce": 6.284721851348877, "genuineness": 4.419482707977295, "identity": 0.45639699697494507, "hypothesis": "Die Tür ist noch offen, ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/19d47b837ad0f041ba311e9a8b2e45831ab541bbf05d9df67bf82b41f7590952.mp3" }, { "id": "emo_Amusement-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-0", "key": "19e759ee571e6c1fa1e1b8916b32c06ca9d5083098e9e737cd0cc97368fb37fa", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e794926a8c199b20e470cba290672710033a8a122854355ce8d24724f2a2184c", "generation_seconds_batch": 21.91472171503119, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2943968772888184, "target_z": 2.093749901249186, "ce": 6.300607204437256, "genuineness": 4.457139015197754, "identity": 0.5355894565582275, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/19e759ee571e6c1fa1e1b8916b32c06ca9d5083098e9e737cd0cc97368fb37fa.mp3" }, { "id": "emo_Amusement-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-0", "key": "1a395eff8962994e7dbbb1b4b559c4ab871ab1677933c0355ed729a0ff6ca24f", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De deur staat nog open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "23f9dcd9a01554f1ed257d603f29d7fc4f28c930ea7e972805157d3f693e5bc4", "generation_seconds_batch": 27.78759699303191, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2976233959198, "target_z": 3.249999862607563, "ce": 6.133810997009277, "genuineness": 4.400654315948486, "identity": 0.6336402893066406, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/1a395eff8962994e7dbbb1b4b559c4ab871ab1677933c0355ed729a0ff6ca24f.mp3" }, { "id": "emo_Amusement-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-1", "key": "1a3f2f05d2b8f435e90887f7804abdea87e60cc6d356b9c41fae7750b8a211d2", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "483e18fae7b89e358f82d25cd89045d07c871e2d564c4c325d9115743e01e8d0", "generation_seconds_batch": 18.119773142039776, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5655391216278076, "target_z": 2.40624982396594, "ce": 6.117925643920898, "genuineness": 4.268857479095459, "identity": 0.006127834320068359, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/1a3f2f05d2b8f435e90887f7804abdea87e60cc6d356b9c41fae7750b8a211d2.mp3" }, { "id": "emo_Amusement-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-0", "key": "1a89b21de9baf336aa4b74611dfa58ca5497cb0ad4c2fa458ba3ce49404b5178", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De deur staat nog open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "1b98c92bfb6d2e4d0691e16627168671350f12fec017af69dc036e840e596e85", "generation_seconds_batch": 16.761026681982912, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6875531673431396, "target_z": 2.5468748304062103, "ce": 5.772419452667236, "genuineness": 4.2751336097717285, "identity": 0.34444886445999146, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/1a89b21de9baf336aa4b74611dfa58ca5497cb0ad4c2fa458ba3ce49404b5178.mp3" }, { "id": "emo_Amusement-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-0", "key": "1ab8f50386bd6b443125d6d02d5611b4210b3dd1154e6c687c52be81c0b4bfbf", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The door is still open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "1a6b70917a23ad546fc9bb55fae234ef190e668a666eeb9b48b7d33dde539dff", "generation_seconds_batch": 16.086044667987153, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1994972229003906, "target_z": 1.9843750794300028, "ce": 6.070269584655762, "genuineness": 3.5471129417419434, "identity": 0.40819454193115234, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/1ab8f50386bd6b443125d6d02d5611b4210b3dd1154e6c687c52be81c0b4bfbf.mp3" }, { "id": "emo_Amusement-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-0", "key": "1c042d08a2414b1ddd7b451e1b88bba9a38eb5a2eb7afc71241424ed838b5a66", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De deur staat nog open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "19934d31e1ade8ce52dcb5f9dce2031d30dc9f2b35f802c17e9e68f33b8114d8", "generation_seconds_batch": 27.23353055701591, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.009697437286377, "target_z": 1.765624886221888, "ce": 6.165581703186035, "genuineness": 4.111956596374512, "identity": 0.3749070167541504, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/1c042d08a2414b1ddd7b451e1b88bba9a38eb5a2eb7afc71241424ed838b5a66.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": "1c98eb148469da04893f9e9ea19b5c793949cf253bfab19b82fca52999bddf03", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "16dda57df1319656caef2f0acf7b010411e48714e5f3e5a699f3776923edbd84", "generation_seconds_batch": 18.054332925006747, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.663991093635559, "target_z": 1.367187505366892, "ce": 6.41180419921875, "genuineness": 4.268857479095459, "identity": 0.5728151798248291, "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_Amusement/1c98eb148469da04893f9e9ea19b5c793949cf253bfab19b82fca52999bddf03.mp3" }, { "id": "emo_Amusement-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-0", "key": "1ca7107f4d0f433838d2922c79b4c3f18fe5d61ca9506edf359d2846a00a0d2d", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "26f9f6b31e056126af81798e28184f08b6f4bb8bac91132106b1896a9cd635b7", "generation_seconds_batch": 25.467357915942557, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.497753620147705, "target_z": 2.32812491198297, "ce": 6.1894097328186035, "genuineness": 4.218649387359619, "identity": 0.46223247051239014, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/1ca7107f4d0f433838d2922c79b4c3f18fe5d61ca9506edf359d2846a00a0d2d.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": "1cc7d257bf339e7b0e69521761919687a82979b0f74afa25531919fb57e68f9b", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "60005cdc462d4f8ab807e44d3b1c620871d94d78f02640a0f662e2236ee0a33f", "generation_seconds_batch": 21.101786165032536, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0639259815216064, "target_z": 1.8281249806791886, "ce": 6.23706579208374, "genuineness": 4.3504462242126465, "identity": 0.6412960290908813, "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_Amusement/1cc7d257bf339e7b0e69521761919687a82979b0f74afa25531919fb57e68f9b.mp3" }, { "id": "emo_Amusement-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-0", "key": "1d0ef650c7e8ba71bac3d08a08fea356a552bda84d2d3490f80736c3fb3b25a7", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "c803199f8bd6e666c2eb1f87987965b633ef52d715b1cd4209fbc5b5ecd26ec9", "generation_seconds_batch": 25.341856165090576, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9215762615203857, "target_z": 1.6640624731655396, "ce": 6.372091293334961, "genuineness": 4.394378662109375, "identity": 0.3671247661113739, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/1d0ef650c7e8ba71bac3d08a08fea356a552bda84d2d3490f80736c3fb3b25a7.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_Amusement", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": "1408956cf696667fc64ce68fe5df3aa722be6470d8f41f5f59e7692e539732df", "generation_seconds_batch": 16.98460360302124, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.726855456829071, "target_z": 0.2871093538007763, "ce": 6.340320587158203, "genuineness": 4.331617832183838, "identity": 0.6098619103431702, "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_Amusement/1d559e6da25f8bbacc3b53d5880369445633ce7ab0125ca7b07093108b8c8de3.mp3" }, { "id": "emo_Amusement-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-1", "key": "1d63510dcee3c8d09faf67d1dccd07bf43aa6f231090d02e8f635b95bfc77939", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "0dc102d0d7c7e07b40c1a6c366fc00798706a3f1053be959d3f7ee3f9144c0eb", "generation_seconds_batch": 24.564030235051177, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1588258743286133, "target_z": 1.9375000772832458, "ce": 6.165581703186035, "genuineness": 4.507347106933594, "identity": 0.6498166918754578, "hypothesis": "J'ai trouvé la 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_Amusement/1d63510dcee3c8d09faf67d1dccd07bf43aa6f231090d02e8f635b95bfc77939.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_Amusement", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": "5ac83ed989245292398d63b2fd26a919f17cd286b062a57d4fc086f4c6f96aca", "generation_seconds_batch": 18.587327846093103, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.396824449300766, "target_z": -0.09326171157178184, "ce": 6.1894097328186035, "genuineness": 4.482243061065674, "identity": 0.5542376041412354, "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_Amusement/1d829402ab2176d2024ae3e918286a39ec094d9a5299caa0e048ba37912e1579.mp3" }, { "id": "emo_Amusement-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-1", "key": "1d98dcc3802c27bbba2ef7472ae92cdad5bcd8c29e97855785c44c2a6d93840e", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9e06e8ee2f6ecc493e0179bfbdc3d66e1b74cd9d43a5593f449a3ee18162c8cc", "generation_seconds_batch": 24.705629062023945, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8876835107803345, "target_z": 1.6250000171740546, "ce": 6.395919322967529, "genuineness": 4.20609712600708, "identity": 0.4421318769454956, "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_Amusement/1d98dcc3802c27bbba2ef7472ae92cdad5bcd8c29e97855785c44c2a6d93840e.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": "1dbef719ef2cb9b52be4d474b2d002bedaf145051968d5a62126023cbb0c96c6", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "43c5137b1d7ed87287008b5bcd018886b2e5d3fbdf5d1aa9f91e2ae07cfcace5", "generation_seconds_batch": 15.970181567943655, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.728224515914917, "target_z": 2.5937498325529673, "ce": 6.459460258483887, "genuineness": 4.519899368286133, "identity": 0.5930604934692383, "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_Amusement/1dbef719ef2cb9b52be4d474b2d002bedaf145051968d5a62126023cbb0c96c6.mp3" }, { "id": "emo_Amusement-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-0", "key": "1e0ff475f11df615afbc9c78f91a769addb7baea2277388b489cba7600f9cc4b", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "3f251fe50268d81233dd520dff5c92c11cea14d178454c12265b99268f238f2f", "generation_seconds_batch": 16.91480943595525, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1725456714630127, "target_z": 0.8007812752243928, "ce": 6.133810997009277, "genuineness": 4.268857479095459, "identity": 0.44816991686820984, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/1e0ff475f11df615afbc9c78f91a769addb7baea2277388b489cba7600f9cc4b.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": "1e6b83ea0eb735d7640f0b386d2c878c9513632ca18a304427a5f471182a9d17", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "308627ab1ccf373ee355318946d7938b8d7e824d9595ffa1ab60eff604291295", "generation_seconds_batch": 19.573803259059787, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8605692386627197, "target_z": 1.5937499699454043, "ce": 6.252951145172119, "genuineness": 4.394378662109375, "identity": 0.48483753204345703, "hypothesis": "Die Schlüssel liegen auf dem Küchentisch. Ich suchte in der Schublade daneben dem Fenster. Nimm sie mit, wenn du gehst.", "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_Amusement/1e6b83ea0eb735d7640f0b386d2c878c9513632ca18a304427a5f471182a9d17.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_Amusement", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": "ee670167685cf136db2236569d3ffe13516bc54b6476bd836a582bfa67c2c8c7", "generation_seconds_batch": 16.98460360302124, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1183172464370728, "target_z": 0.7382813181595294, "ce": 6.1894097328186035, "genuineness": 4.394378662109375, "identity": 0.6424994468688965, "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_Amusement/1eaf0e0e2c966186cf6ada2de41819a315f8b1b1eeeeef5a84a28dd582998db8.mp3" }, { "id": "emo_Amusement-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-0", "key": "1eca8f109337730c061ac4f998ecef6bbc569faeefcf2da87490dd5e9929990e", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "3fa970b4554c5194da5782e1ee83ea68ff89c36c09ddcf12bb9355c698edf723", "generation_seconds_batch": 24.144701690995134, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0029189586639404, "target_z": 1.7578124774590533, "ce": 6.260893821716309, "genuineness": 4.444586753845215, "identity": 0.6380192637443542, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/1eca8f109337730c061ac4f998ecef6bbc569faeefcf2da87490dd5e9929990e.mp3" }, { "id": "emo_Amusement-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-1", "key": "1f3644603f4eb2dce9e8855822b881f35715ec2084d30169003055b5a13e0bb5", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "05a706ebbba2c0c1b1143074edf8e29e7e3d810825cc03e2a5dff0b8ecabd443", "generation_seconds_batch": 21.260337637970224, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.226611375808716, "target_z": 2.015624989266216, "ce": 6.515059471130371, "genuineness": 4.099404335021973, "identity": 0.5827596187591553, "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_Amusement/1f3644603f4eb2dce9e8855822b881f35715ec2084d30169003055b5a13e0bb5.mp3" }, { "id": "emo_Amusement-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-0", "key": "20e30d22220a859cb4b9f1325098acf347ca87e26b8e673f376575aa4eb6c270", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The door is still open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "1513cc352727d970d1456d83fd904233c75ff65a727f47751ead155fdb8f718a", "generation_seconds_batch": 18.750275145983323, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.758890986442566, "target_z": 1.4765626019709495, "ce": 6.165581703186035, "genuineness": 3.7416701316833496, "identity": 0.3637130856513977, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/20e30d22220a859cb4b9f1325098acf347ca87e26b8e673f376575aa4eb6c270.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": "20ed137223ab0aaa7cd37d60e83c9a9cad8fc4f5d6b51a1a5b5a1c87a24d8672", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I wrote the number on the envelope.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5fc912bf51f892d7dde361bcfa05b82306a971ac7cdf7e6217344629b60117b4", "generation_seconds_batch": 17.635579205933027, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6911053657531738, "target_z": 1.3984375525955424, "ce": 6.324435234069824, "genuineness": 4.030367851257324, "identity": 0.4502791166305542, "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_Amusement/20ed137223ab0aaa7cd37d60e83c9a9cad8fc4f5d6b51a1a5b5a1c87a24d8672.mp3" }, { "id": "emo_Amusement-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-1", "key": "217f13bff31c93acc8af153ec32ada051f4aa020e6e99cfe086e75a041187c04", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "0aad75c07f44f1069547ee1f03d082e7c700f3125d1d13bafffc23e76fb84e36", "generation_seconds_batch": 24.01405820308719, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0978188514709473, "target_z": 1.8671875740631108, "ce": 6.252951145172119, "genuineness": 4.519899368286133, "identity": 0.7337143421173096, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/217f13bff31c93acc8af153ec32ada051f4aa020e6e99cfe086e75a041187c04.mp3" }, { "id": "emo_Amusement-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-0", "key": "21c342733146b1e41ef90f933a707bfa3b55c53657e17b3b866e2c1ebf7571b5", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "0dc9f22ae43ed07dc1fec1e515445db8f4403d38c8007332b2350faa0eb50fc1", "generation_seconds_batch": 23.9782854730729, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7792266607284546, "target_z": 1.500000103044328, "ce": 5.990842819213867, "genuineness": 4.042920112609863, "identity": 0.6072207093238831, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/21c342733146b1e41ef90f933a707bfa3b55c53657e17b3b866e2c1ebf7571b5.mp3" }, { "id": "emo_Amusement-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-1", "key": "22e6b752b797e2186b85acb323a697092cc880d551a45a376ac3a88c0623a39a", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "476e32e425484f57effaae8e32f75f2ed2b43651aa1fa5331ab3d215f64f9083", "generation_seconds_batch": 18.1234682550421, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3621826171875, "target_z": 2.17187508801703, "ce": 6.332377910614014, "genuineness": 3.8546390533447266, "identity": 0.5774161219596863, "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_Amusement/22e6b752b797e2186b85acb323a697092cc880d551a45a376ac3a88c0623a39a.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": "233371c6d46691d47f921aa1d6ab698986b67fe966dbac64f58a767c05a5c912", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "c26e9d78d9f5c88b1ed5383bc90cc3c5929247d5157142ca65732910c34e2d96", "generation_seconds_batch": 29.783178596990183, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5248677730560303, "target_z": 2.3593748218191832, "ce": 6.038498878479004, "genuineness": 4.2249250411987305, "identity": 0.5815789103507996, "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_Amusement/233371c6d46691d47f921aa1d6ab698986b67fe966dbac64f58a767c05a5c912.mp3" }, { "id": "emo_Amusement-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-0", "key": "23c16da175dd219e95013c43d04a13f5e52bd2cfa236b3a413d34633932453d6", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The door is still open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "9f5ce82a30c33d54441a49280fdbed839f379d5aab97bafa49aec89c2dd55e9f", "generation_seconds_batch": 16.086044667987153, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8809049129486084, "target_z": 1.6171874710187828, "ce": 6.141753673553467, "genuineness": 4.042920112609863, "identity": 0.38011476397514343, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/23c16da175dd219e95013c43d04a13f5e52bd2cfa236b3a413d34633932453d6.mp3" }, { "id": "emo_Amusement-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-0", "key": "2438b6952485dc40d371f8a8d1cf31584f2fda69bef61d1fe25bf8317cd8f0d7", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9b2db7ee7ab1dce32adada7165a527d011e3abe8ba29e98b8eaad6a97fb81e8b", "generation_seconds_batch": 24.40829053998459, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0029189586639404, "target_z": 1.7578124774590533, "ce": 6.23706579208374, "genuineness": 4.331617832183838, "identity": 0.6792482137680054, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/2438b6952485dc40d371f8a8d1cf31584f2fda69bef61d1fe25bf8317cd8f0d7.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": "24715e1ae9be7c51632ff4306c61b5d8cb1c375d8e22d13aa40d5f0bcceb8425", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9c637d3e952a828efeaf7dd153ad6a9b3427f7de9aa39381eeadde748b456461", "generation_seconds_batch": 22.17604653595481, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2572776079177856, "target_z": 0.8984374838993238, "ce": 6.332377910614014, "genuineness": 4.369274139404297, "identity": 0.6622923612594604, "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_Amusement/24715e1ae9be7c51632ff4306c61b5d8cb1c375d8e22d13aa40d5f0bcceb8425.mp3" }, { "id": "emo_Amusement-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-1", "key": "253e28214fa74721301a57890e1be7f39263939307b88b8af5e53a208ef541c9", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I found the little box.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It was beside the old window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "96d84e7bd9df14bc37b89e117b8a159af432cbe29fdd4857113ec97815270e71", "generation_seconds_batch": 24.063946028938517, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8131194114685059, "target_z": 1.539062559035813, "ce": 6.292664527893066, "genuineness": 4.406930446624756, "identity": 0.48541104793548584, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/253e28214fa74721301a57890e1be7f39263939307b88b8af5e53a208ef541c9.mp3" }, { "id": "emo_Amusement-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-0", "key": "255cafb33f5a33706616da1b990ec2abbeaa4856e31b5a6eaf2a89513f710e05", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "ea3e7ec53c9eccf718ebaf3992f61f7105bf99394d89d153d1e127ca6a7d9550", "generation_seconds_batch": 24.404853226966225, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4028539657592773, "target_z": 2.218750090163787, "ce": 5.744620323181152, "genuineness": 3.6663577556610107, "identity": 0.45230633020401, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/255cafb33f5a33706616da1b990ec2abbeaa4856e31b5a6eaf2a89513f710e05.mp3" }, { "id": "emo_Amusement-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-1", "key": "25a9101fd9af408fc29d7594511eab27b3370d022a406c2edc20e31a58ae4180", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "62826cd7585fdc9790bcdfbaab0487149c3f41fa5b0c8add5e9c8d5624590894", "generation_seconds_batch": 23.628680750960484, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.758890986442566, "target_z": 1.4765626019709495, "ce": 6.038498878479004, "genuineness": 4.105680465698242, "identity": 0.4357817471027374, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/25a9101fd9af408fc29d7594511eab27b3370d022a406c2edc20e31a58ae4180.mp3" }, { "id": "emo_Amusement-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-0", "key": "25c6d0e93471413a3d0d0a6ffb2df2f8d19deb0855519f0a6919f4f5734cce9e", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De deur staat nog open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "17d6d759abb1a58e7e58c5cace163bc16ff6dae30ab197fe9e3a24aa18514abb", "generation_seconds_batch": 23.534630861948244, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9963032007217407, "target_z": 0.5976563117192589, "ce": 6.1020402908325195, "genuineness": 4.080576419830322, "identity": 0.6269891858100891, "hypothesis": "De deur 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_Amusement/25c6d0e93471413a3d0d0a6ffb2df2f8d19deb0855519f0a6919f4f5734cce9e.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": "25d26cce62c0be3107d17a776a2317380bcdf35e1a3cd03288f2a547bf3c6b7a", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Escribí el número en el sobre.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "878971e798a0333a2944909a13278e9287174c3c5678cf0707768f8636d77442", "generation_seconds_batch": 15.198533010086976, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9554691314697266, "target_z": 1.7031250665494617, "ce": 6.284721851348877, "genuineness": 4.218649387359619, "identity": 0.6558312177658081, "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_Amusement/25d26cce62c0be3107d17a776a2317380bcdf35e1a3cd03288f2a547bf3c6b7a.mp3" }, { "id": "emo_Amusement-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-0", "key": "25ea90828d0e2995d50698e2b27098fe4e2d1f39668e760395526ec924a4bc45", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5713b333d37e33f1e8378f9aac3889d3133a206f463cbc5d1d05ee03133a8985", "generation_seconds_batch": 24.1704019960016, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.47063946723938, "target_z": 2.296875002146757, "ce": 6.006728172302246, "genuineness": 4.256305694580078, "identity": 0.6466501951217651, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/25ea90828d0e2995d50698e2b27098fe4e2d1f39668e760395526ec924a4bc45.mp3" }, { "id": "emo_Amusement-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-1", "key": "26619aab5da911c025b85edb663e1ad14e2f67e5017676dca99d394ca807a8d2", "bucket": "emo_Amusement", "phase": "wording", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1d1444a7272d788123ba1f1a1d8b666a7870dbf3fa42e9a7400613fd1ea9e06c", "generation_seconds_batch": 17.89434230304323, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7860051393508911, "target_z": 1.5078125118071626, "ce": 6.443574905395508, "genuineness": 4.18099308013916, "identity": 0.4333656430244446, "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_Amusement/26619aab5da911c025b85edb663e1ad14e2f67e5017676dca99d394ca807a8d2.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_Amusement", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": "065e64c796e85930007c31b6ec9ca94092f5c5cfda8ffcaf923e7d7651ac32d6", "generation_seconds_batch": 15.698369250050746, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6861841082572937, "target_z": 0.24023435165401946, "ce": 6.483288764953613, "genuineness": 4.457139015197754, "identity": 0.19336135685443878, "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_Amusement/26d12995a5b024b42cbe037fdee48ffb67b79df656c09f059592185aa881aca9.mp3" }, { "id": "emo_Amusement-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-1", "key": "26d4605475e397843783efd7e0a4d11dd32ce9e8dab900f60c8c1fe2c667fd09", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "02199851406bb1dff45ee3a3f094ff30d8a13876b31eecde2d35ac3d2ec18b06", "generation_seconds_batch": 24.33164233097341, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5655391216278076, "target_z": 2.40624982396594, "ce": 6.23706579208374, "genuineness": 3.7793264389038086, "identity": 0.27796387672424316, "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_Amusement/26d4605475e397843783efd7e0a4d11dd32ce9e8dab900f60c8c1fe2c667fd09.mp3" }, { "id": "emo_Amusement-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-0", "key": "26ecb99e42cc9cb38315849dafee2fec6b62e5ea94914bca2babab4776d86343", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De deur staat nog open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "62785aee8de09c8923f43b5d0e8f16d1767b489fd6fa8f0e6c25107801f4362e", "generation_seconds_batch": 18.096010698005557, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8334550857543945, "target_z": 1.5625000601091912, "ce": 6.0305562019348145, "genuineness": 4.168440818786621, "identity": 0.5912612676620483, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/26ecb99e42cc9cb38315849dafee2fec6b62e5ea94914bca2babab4776d86343.mp3" }, { "id": "emo_Amusement-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-0", "key": "27215414850b2fe8b8c4eab94a3e126b49863323e284a8e66716a65f5ea662f1", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The door is still open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "a2888520f7bbe1735787674f94f058d2f4e7439065fb693f92253c541da07e47", "generation_seconds_batch": 24.669070275966078, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2130541801452637, "target_z": 1.999999896955672, "ce": 6.268836498260498, "genuineness": 4.143336772918701, "identity": 0.2847605347633362, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/27215414850b2fe8b8c4eab94a3e126b49863323e284a8e66716a65f5ea662f1.mp3" }, { "id": "emo_Amusement-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-0", "key": "27c316d2a2c13ef2ddf5690943109140ba9d1ff2dd984cbbc1ae99dd1e1c1bb0", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "66f6bb04242d7f8dd68a1fa0d382fcc685a603dc93b1b890b5528e9e8e8c5d26", "generation_seconds_batch": 24.46483776497189, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.863795757293701, "target_z": 2.7499999313037815, "ce": 6.109982967376709, "genuineness": 4.344170093536377, "identity": 0.3961107134819031, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/27c316d2a2c13ef2ddf5690943109140ba9d1ff2dd984cbbc1ae99dd1e1c1bb0.mp3" }, { "id": "emo_Amusement-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-0", "key": "28903c2984bd6ead08a6b4c1bbf2a78d8c66c8e1f86ac84ad3011aa4e55d5fee", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De deur staat nog open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "e11af756c11c584baa3d14477a2847e13c3e8976f7a33b4f94275965e11bb600", "generation_seconds_batch": 22.85491582704708, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.972252607345581, "target_z": 2.8749998454335084, "ce": 6.046441555023193, "genuineness": 4.042920112609863, "identity": 0.3783937692642212, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar, wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/28903c2984bd6ead08a6b4c1bbf2a78d8c66c8e1f86ac84ad3011aa4e55d5fee.mp3" }, { "id": "emo_Amusement-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-1", "key": "29bb0283fd15c5793590e7fac99159fd36c9a2371acb6a9b9f6d4530708a7cc4", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "4a74d87831fa1651700b51683bef97c0d14c2cd887416edf492195433ec23f3c", "generation_seconds_batch": 24.183834964991547, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.084261655807495, "target_z": 1.8515624817525669, "ce": 6.197352409362793, "genuineness": 4.118232727050781, "identity": 0.6925846338272095, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/29bb0283fd15c5793590e7fac99159fd36c9a2371acb6a9b9f6d4530708a7cc4.mp3" }, { "id": "emo_Amusement-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-0", "key": "2a51b2bcb6bc51407c7c8969b532b8a303663d1dc1a4273e763c37aacb2dcada", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De deur staat nog open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "cb8ca4cbfd92de20e7460ffe177a670682933c44e58388fdee824f3ad55f9f07", "generation_seconds_batch": 27.23353055701591, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8537907600402832, "target_z": 1.5859375611825697, "ce": 6.046441555023193, "genuineness": 4.20609712600708, "identity": 0.5457203388214111, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/2a51b2bcb6bc51407c7c8969b532b8a303663d1dc1a4273e763c37aacb2dcada.mp3" }, { "id": "emo_Amusement-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-1", "key": "2a93c5b822b80d7ea698dc08a0e61c2b91eb55cd5b16feef121de696dc068fa1", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "28164ce8355bdf488d5276ee56d10a37bde1f11dddc064e07b3c0f130fc45d40", "generation_seconds_batch": 22.471723788999952, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3250632286071777, "target_z": 0.9765625332747309, "ce": 6.292664527893066, "genuineness": 4.419482707977295, "identity": 0.6920205950737, "hypothesis": "J'ai trouvé la 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_Amusement/2a93c5b822b80d7ea698dc08a0e61c2b91eb55cd5b16feef121de696dc068fa1.mp3" }, { "id": "emo_Amusement-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-1", "key": "2a9d10ab173dd1a8cc83dc5cde4978721ecd513382f3b5ddccb2b3fbdd9434d9", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "d6fa95aac411e8351a052eb58d765097697654fe3c39e7aedc8206df63916388", "generation_seconds_batch": 24.183834964991547, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3318417072296143, "target_z": 0.9843749420375656, "ce": 6.0146708488464355, "genuineness": 4.20609712600708, "identity": 0.6909037232398987, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/2a9d10ab173dd1a8cc83dc5cde4978721ecd513382f3b5ddccb2b3fbdd9434d9.mp3" }, { "id": "emo_Amusement-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-0", "key": "2b435100183b2b949b17c251c2bba5989798f6c2132c154df6116e900df421b1", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "acbcc8544f65def5b87d3cade5685db73565b0c90e1f9645c632a8eaef277e3b", "generation_seconds_batch": 20.652963318047114, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7963356971740723, "target_z": 0.3671875053668921, "ce": 6.157639026641846, "genuineness": 4.406930446624756, "identity": 0.5730501413345337, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/2b435100183b2b949b17c251c2bba5989798f6c2132c154df6116e900df421b1.mp3" }, { "id": "emo_Amusement-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-0", "key": "2b4cf75221ee5669ae078fed8fc2a956b8447002669a28415b8395dc57a37730", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1b5d30ca2aa19de737292d5c61aef1aabbf41245c02c445041307075600d39d8", "generation_seconds_batch": 23.102491695899516, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.389296770095825, "target_z": 2.203124997853243, "ce": 6.125868320465088, "genuineness": 4.369274139404297, "identity": 0.49616745114326477, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/2b4cf75221ee5669ae078fed8fc2a956b8447002669a28415b8395dc57a37730.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": "2b71b31d75f41e59b408c17068f244eaae1f91d56dde1c84c761e301917bd1ae", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2b20ea724c4e7fe49b9dc98ed2ee0b4888b862c85d087dcbdbc493314901dbf8", "generation_seconds_batch": 18.680346278939396, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.413184404373169, "target_z": 1.0781249463310791, "ce": 6.308549880981445, "genuineness": 4.231201171875, "identity": 0.5038456916809082, "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_Amusement/2b71b31d75f41e59b408c17068f244eaae1f91d56dde1c84c761e301917bd1ae.mp3" }, { "id": "emo_Amusement-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-1", "key": "2bd65d01ab706fb645b07a441b201c1d5dc9fceeb97b383a29cdfa8eab1df385", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "640424055749b5d2969d1dbce02a87cfc0aca65ee52bbf0a52696ab9f0e73f04", "generation_seconds_batch": 19.182055918034166, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9215762615203857, "target_z": 1.6640624731655396, "ce": 6.062326908111572, "genuineness": 4.595211505889893, "identity": 0.6536527276039124, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/2bd65d01ab706fb645b07a441b201c1d5dc9fceeb97b383a29cdfa8eab1df385.mp3" }, { "id": "emo_Amusement-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-0", "key": "2c57283bfa5dc06cf715cbfddf2ac0c4f4282c149fec28a84f9d210064bcc8f1", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "d34243daaf14e02f67716dd5b5969706766b146e2ef7a59fdd6543d107f6254c", "generation_seconds_batch": 21.568640187964775, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7827786207199097, "target_z": 0.35156255044878554, "ce": 6.324435234069824, "genuineness": 4.231201171875, "identity": 0.3837146759033203, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/2c57283bfa5dc06cf715cbfddf2ac0c4f4282c149fec28a84f9d210064bcc8f1.mp3" }, { "id": "emo_Amusement-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-1", "key": "2cf24a2200d229e20db307bd53eb1694f9521786225476dd34c87854b8dcbb8c", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "312ffdb9e4de4d5bd93bb787a6f90df099521b4b75960cc3bb8c8ae213fdc4fb", "generation_seconds_batch": 24.414886599057354, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0264811515808105, "target_z": 2.9374999398908086, "ce": 6.054384231567383, "genuineness": 3.886019229888916, "identity": 0.34882867336273193, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/2cf24a2200d229e20db307bd53eb1694f9521786225476dd34c87854b8dcbb8c.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": "2d23109836452df2f5c4188a8ea8201ca88d1d657afc91bf162711faeea76295", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The road turns left behind the bridge.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ebef09343f7421daa4c1b76d6c3caa538097b919a3c10825c2ee27bd09a58ef6", "generation_seconds_batch": 19.422961750999093, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7031305432319641, "target_z": 0.25976564834598054, "ce": 6.324435234069824, "genuineness": 3.9425034523010254, "identity": 0.33069467544555664, "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_Amusement/2d23109836452df2f5c4188a8ea8201ca88d1d657afc91bf162711faeea76295.mp3" }, { "id": "emo_Amusement-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-1", "key": "2d61659800f4ff931e2e56f07ca02aab34d0cdfbe4302c8e5957ec9dc7428863", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "ce348a8de412e15d5f08f8ffa8a14068a12bf44b1944ea1d597e96241d847d8b", "generation_seconds_batch": 21.06697072996758, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2504990100860596, "target_z": 0.8906249377440519, "ce": 6.284721851348877, "genuineness": 4.369274139404297, "identity": 0.6826717853546143, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/2d61659800f4ff931e2e56f07ca02aab34d0cdfbe4302c8e5957ec9dc7428863.mp3" }, { "id": "emo_Amusement-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-1", "key": "2dafb7b0cd88ac8c1b05316eb694955e19b6d0a2b477e7667af527479698f3b6", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "9d6ed27d9afa8b6ae4509a05be5cf10001edd8271bad36bbb17f9b7ab1a86446", "generation_seconds_batch": 22.481750952079892, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5351985692977905, "target_z": 1.2187500901637869, "ce": 6.38003396987915, "genuineness": 4.093128204345703, "identity": 0.49703511595726013, "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_Amusement/2dafb7b0cd88ac8c1b05316eb694955e19b6d0a2b477e7667af527479698f3b6.mp3" }, { "id": "emo_Amusement-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-0", "key": "2db95337c5625d0d51283984497d6b9ba20e06e517721ffd4dc7c1c1d9ddac5e", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The door is still open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "0065af616578b7cf4e338350396a00cd2aae94ffe0e7992de301ab0c9cefe8f3", "generation_seconds_batch": 23.947383363032714, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.182713508605957, "target_z": 0.8125000257610819, "ce": 6.316492557525635, "genuineness": 4.2249250411987305, "identity": 0.24399474263191223, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/2db95337c5625d0d51283984497d6b9ba20e06e517721ffd4dc7c1c1d9ddac5e.mp3" }, { "id": "emo_Amusement-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-0", "key": "2dc196e00c984a7aca1e948c3669e7d221841e1b36323a825075765775716a99", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The door is still open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "5eca542f9242c3b41c0d34ebd13d4561382aacd406744160ce24de4452b033ab", "generation_seconds_batch": 24.23870539094787, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8809049129486084, "target_z": 1.6171874710187828, "ce": 6.181467056274414, "genuineness": 3.9425034523010254, "identity": 0.33769094944000244, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/2dc196e00c984a7aca1e948c3669e7d221841e1b36323a825075765775716a99.mp3" }, { "id": "emo_Amusement-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-1", "key": "2e24a6be1ae500290ede5bd784bbf9f06b0bf6d9c841de714499df1939e587dc", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "f708387976d4740c0d82c34ed7d55e24ace468cb0defa7a9cac46b62b11803f4", "generation_seconds_batch": 21.666609402978793, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5655391216278076, "target_z": 2.40624982396594, "ce": 6.109982967376709, "genuineness": 4.068024158477783, "identity": 0.6493779420852661, "hypothesis": "J'ai trouvé la 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_Amusement/2e24a6be1ae500290ede5bd784bbf9f06b0bf6d9c841de714499df1939e587dc.mp3" }, { "id": "emo_Amusement-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-1", "key": "2e69a0a3fe99cd37a90d9dc40602298110bddd6b8bf535d7ce086cecf20e499c", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "b2fde27c431ef8784b7d71966c654fb5129fa986a431714e4cea1f3ed9fc29ea", "generation_seconds_batch": 21.70721016090829, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.226611375808716, "target_z": 2.015624989266216, "ce": 6.022613525390625, "genuineness": 4.068024158477783, "identity": 0.7228342890739441, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/2e69a0a3fe99cd37a90d9dc40602298110bddd6b8bf535d7ce086cecf20e499c.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": "2ec123c43805b9a2caf4afc3d325252c3be7bc201e55a66538f2dba5571e576f", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4269770ab2b65e38d992676f7c3b48c0756bc5105f5dea3fe5c52fcc1ba68e24", "generation_seconds_batch": 29.612505786004476, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1384902000427246, "target_z": 1.9140625762098675, "ce": 6.284721851348877, "genuineness": 4.457139015197754, "identity": 0.45883458852767944, "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_Amusement/2ec123c43805b9a2caf4afc3d325252c3be7bc201e55a66538f2dba5571e576f.mp3" }, { "id": "emo_Amusement-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-0", "key": "2f6503ed6ace92d9cd89c768c6f61e6d3462b24ff83a484adfc833ceee582e22", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "cf94adfa69dc06376d9ebe7056f45ca20772bf5ff2301a0a0f9bc1fef5beb67d", "generation_seconds_batch": 23.789832510985434, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3079540729522705, "target_z": 2.1093749935597295, "ce": 5.982900142669678, "genuineness": 4.231201171875, "identity": 0.5250287652015686, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/2f6503ed6ace92d9cd89c768c6f61e6d3462b24ff83a484adfc833ceee582e22.mp3" }, { "id": "emo_Amusement-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-1", "key": "304d1d28e1b43c98c0cff6335ee7df7dbde02c7156de8e3a9134ad79302f67d3", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I found the little box.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It was beside the old window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8a2484d0bdddd75ee2ec2bcd2fd290917e0166ace492a2b922cd15182f2ebe4a", "generation_seconds_batch": 25.433923322940245, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.863795757293701, "target_z": 2.7499999313037815, "ce": 6.221180438995361, "genuineness": 4.024092197418213, "identity": 0.3222878575325012, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/304d1d28e1b43c98c0cff6335ee7df7dbde02c7156de8e3a9134ad79302f67d3.mp3" }, { "id": "emo_Amusement-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-0", "key": "3111b7d5c7d9912dd5cb68a623780b80d417f9c26eb81e38e2aa315df619ef29", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De deur staat nog open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "c7c458ffb9db5efdb1fe7c5cfbe88fdd3da7cef05d8032aabf38a84b5b58a82f", "generation_seconds_batch": 27.296263516996987, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.592653512954712, "target_z": 2.4375000085870275, "ce": 5.927301406860352, "genuineness": 4.118232727050781, "identity": 0.11974555999040604, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/3111b7d5c7d9912dd5cb68a623780b80d417f9c26eb81e38e2aa315df619ef29.mp3" }, { "id": "emo_Amusement-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-0", "key": "3171625f88e59fe4f7e8e4e0f6b4472428131d255d264d3fdbf59b903f01d68f", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "ce39e951f409c6cbf480e486de2df6bb867ad4466f17f2f58c274d85bb217517", "generation_seconds_batch": 16.972640816005878, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.426741600036621, "target_z": 1.093750038641623, "ce": 6.213237762451172, "genuineness": 4.381826400756836, "identity": 0.6047699451446533, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/3171625f88e59fe4f7e8e4e0f6b4472428131d255d264d3fdbf59b903f01d68f.mp3" }, { "id": "emo_Amusement-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-1", "key": "318051b7d0034eaadb46a6f32945fa2105ce4a720d176811ca5ddf8899329525", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I found the little box.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It was beside the old window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dad9a09d4786105367a9202753e52c96ff305ca71e191569cfc2c479fed5bacd", "generation_seconds_batch": 23.549201735993847, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.677222728729248, "target_z": 3.687499974238918, "ce": 5.959072113037109, "genuineness": 4.080576419830322, "identity": 0.38960719108581543, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/318051b7d0034eaadb46a6f32945fa2105ce4a720d176811ca5ddf8899329525.mp3" }, { "id": "emo_Amusement-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-1", "key": "31f5f434639fd30b7116841429177003c5a518ed547f94a868d87d76da51e0a9", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "00be87a5c34bf495837ad9c8c0c63e8705ce371721b90d2785cff811731ca735", "generation_seconds_batch": 23.107993464916945, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2976233959198, "target_z": 3.249999862607563, "ce": 5.990842819213867, "genuineness": 4.118232727050781, "identity": 0.31832683086395264, "hypothesis": "Ik heb het kleine doosje gevonden. Het stopt naast het oude raam. We kunnen er samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/31f5f434639fd30b7116841429177003c5a518ed547f94a868d87d76da51e0a9.mp3" }, { "id": "emo_Amusement-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-1", "key": "31f8c7379ee5f12c58d2349cc232e59344ce50c71dba6eb6aa8e609520202fa0", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 127, "seconds_generated": 10.16, "mp3_sha256": "1554aca092f06019aee5a9248e40dbe81473dde498f052eb297948dfba67a7f3", "generation_seconds_batch": 23.370527168968692, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3621826171875, "target_z": 2.17187508801703, "ce": 6.0305562019348145, "genuineness": 3.823258876800537, "identity": 0.5309450626373291, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/31f8c7379ee5f12c58d2349cc232e59344ce50c71dba6eb6aa8e609520202fa0.mp3" }, { "id": "emo_Amusement-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-0", "key": "329102dc0c1789a908459144d3a915576eadd65718b4c12cf6e0894ec011f073", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9a12979f59eb78def0aead4b5071466dee132be119dbe1269651558d12083d45", "generation_seconds_batch": 22.548589071957394, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6333248615264893, "target_z": 2.484375010733784, "ce": 6.205295085906982, "genuineness": 4.293961524963379, "identity": 0.44970935583114624, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/329102dc0c1789a908459144d3a915576eadd65718b4c12cf6e0894ec011f073.mp3" }, { "id": "emo_Amusement-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-1", "key": "32b04bc78020f3f4b8f72b1e826ea86a27d523abaf69116d3968af0acb502809", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "b92650dcbb6da4615437a24c03690fbd5970a30477c09478666bda4e1acd9d66", "generation_seconds_batch": 21.800766972941346, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7792266607284546, "target_z": 1.500000103044328, "ce": 6.284721851348877, "genuineness": 4.356721878051758, "identity": 0.7532797455787659, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/32b04bc78020f3f4b8f72b1e826ea86a27d523abaf69116d3968af0acb502809.mp3" }, { "id": "emo_Amusement-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-0", "key": "330f16ebf922aad4e9b6c4aad92f1db039f735539418f33cdb6eca11ae4aa497", "bucket": "emo_Amusement", "phase": "wording", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "0b67c35e3113331ec6457574567e38e68127f697b81bd311e412badc9837a3e8", "generation_seconds_batch": 20.07572298590094, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.535784900188446, "target_z": 0.06689455721234043, "ce": 6.229123115539551, "genuineness": 4.582659721374512, "identity": 0.5314067602157593, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/330f16ebf922aad4e9b6c4aad92f1db039f735539418f33cdb6eca11ae4aa497.mp3" }, { "id": "emo_Amusement-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-0", "key": "3317dcb863603bf4132f52c0e0561f24bc50e335bc26c22bf97a958802ca27f3", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The door is still open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "d8b22888a0a4e0db7704efbc7712faa1d783ca525c20adedaf22b090f35fbf13", "generation_seconds_batch": 23.662918975926004, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.840233564376831, "target_z": 1.570312468872026, "ce": 6.221180438995361, "genuineness": 4.030367851257324, "identity": 0.3135731816291809, "hypothesis": "The 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_Amusement/3317dcb863603bf4132f52c0e0561f24bc50e335bc26c22bf97a958802ca27f3.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": "3317e34b53239099dbffd15a7859c0c209ef3e94d332139eec076d9e35023df5", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "83703d369c2b5c83149e4b1170ac34718d4a8288afe61f5291188eb8b67c3591", "generation_seconds_batch": 15.15159706294071, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6875531673431396, "target_z": 2.5468748304062103, "ce": 6.1020402908325195, "genuineness": 4.381826400756836, "identity": 0.6914020776748657, "hypothesis": "De weg gaat linksaf naar de brug. Loop verder. Tot aan het kleine houten hek. Ik wacht aan de andere kant.", "wer": 0.047619047619047616, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/3317e34b53239099dbffd15a7859c0c209ef3e94d332139eec076d9e35023df5.mp3" }, { "id": "emo_Amusement-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-1", "key": "33a696161fbbf7d46b3acefd8a0b4fc4cb2b13289746166fd340a5f64b2c80ac", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "41888fcd503263e0092e33e1e1bfb87ab5e402dfa42362564ef632e78d38f3c2", "generation_seconds_batch": 23.04370944702532, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6604390144348145, "target_z": 2.5156249205699974, "ce": 5.9431867599487305, "genuineness": 4.080576419830322, "identity": 0.5600665807723999, "hypothesis": "Ik 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_Amusement/33a696161fbbf7d46b3acefd8a0b4fc4cb2b13289746166fd340a5f64b2c80ac.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_Amusement", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": "c39e33a249b6fb598a1ecadcfda46cc574ca33cf63190c8719b160dc42141d7c", "generation_seconds_batch": 18.52951063401997, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4766843318939209, "target_z": -0.0012206974562202434, "ce": 6.078212261199951, "genuineness": 4.3504462242126465, "identity": 0.739425003528595, "hypothesis": "De weg gaat linksaf na de brug. Loop verder tot aan het kleine houten hek. Ik wacht aan de andere kant.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/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_Amusement", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": "097e62c22f8ca72e5bead4e69a4c6b44900e50c911c086b1c7605d3f3c305878", "generation_seconds_batch": 17.03795072308276, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23202075064182281, "target_z": -0.2832031322453043, "ce": 6.475345611572266, "genuineness": 4.268857479095459, "identity": 0.3807485103607178, "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_Amusement/347b084eb1c87968a3fc14b855043a2de140e81cf0874b7d65525285bfb31414.mp3" }, { "id": "emo_Amusement-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-1", "key": "34800ed89b875a0ef1caa1cc826ee0d4324a80fa1e4b4a87035c6b3ec8ec0779", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "32fd778f573c288a374928c487ce5451a591daf2455956c282547f26ecf8903d", "generation_seconds_batch": 22.901089824037626, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5013056993484497, "target_z": 1.1796874967798647, "ce": 6.1894097328186035, "genuineness": 4.406930446624756, "identity": 0.5183423757553101, "hypothesis": "J'ai trouvé la 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_Amusement/34800ed89b875a0ef1caa1cc826ee0d4324a80fa1e4b4a87035c6b3ec8ec0779.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": "3560e6c29b5b4e83ded0bce6beb0c844fa51ebb653ebf7704f5085698aec94a3", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f01db65becd135e4dd4f1f0b828ec294ce8f9050b09ee27b370848a15ab9b4dc", "generation_seconds_batch": 19.032322156010196, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4962785840034485, "target_z": 0.021362291354127497, "ce": 6.229123115539551, "genuineness": 3.7291181087493896, "identity": 0.524782657623291, "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_Amusement/3560e6c29b5b4e83ded0bce6beb0c844fa51ebb653ebf7704f5085698aec94a3.mp3" }, { "id": "emo_Amusement-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-1", "key": "35d4e8b518db39ee8f62ef538ba729802ece89f8f04c9e9942f3d552da4d7b17", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "a0a295444d42d3effef94b08f385d1d3eece331a4c362fc50ea8514b38230bfd", "generation_seconds_batch": 22.549052483052947, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9993669986724854, "target_z": 2.9062500300545957, "ce": 6.062326908111572, "genuineness": 3.9801597595214844, "identity": 0.2482265830039978, "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_Amusement/35d4e8b518db39ee8f62ef538ba729802ece89f8f04c9e9942f3d552da4d7b17.mp3" }, { "id": "emo_Amusement-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-1", "key": "35fc2c0cef3fad13c53d460781b2400297fd9c636cb03204b4390cd0eb0e80da", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "11844271df1dbab10431fb8f9d9cb9dc29086834bef85f8513b94cd6c9e4e230", "generation_seconds_batch": 23.8819565520389, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3079540729522705, "target_z": 2.1093749935597295, "ce": 5.982900142669678, "genuineness": 3.7165660858154297, "identity": 0.18700340390205383, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/35fc2c0cef3fad13c53d460781b2400297fd9c636cb03204b4390cd0eb0e80da.mp3" }, { "id": "emo_Amusement-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-0", "key": "35feefc5fe82cc3e45ea91dd7379786af760061413a0f9e18070fb099e53fa57", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De deur staat nog open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "d7051edb742351d9e694ab05f80048ee84da49a9182829992ff516e0411d2d02", "generation_seconds_batch": 18.676577002974227, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1756093502044678, "target_z": 3.1093748561672925, "ce": 6.0146708488464355, "genuineness": 4.18099308013916, "identity": 0.5998378992080688, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/35feefc5fe82cc3e45ea91dd7379786af760061413a0f9e18070fb099e53fa57.mp3" }, { "id": "emo_Amusement-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-1", "key": "365616e5fb20862af0b34af171ed1ab434c65fce2968e39e22bfa7a564bbc1f3", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "9544617b68d54213d62d14d247d4a8ce31b9e57dba429f66e73a0d6c381ad58e", "generation_seconds_batch": 16.67965994705446, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4674129486083984, "target_z": 1.1406250407883798, "ce": 6.181467056274414, "genuineness": 4.356721878051758, "identity": 0.7725717425346375, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/365616e5fb20862af0b34af171ed1ab434c65fce2968e39e22bfa7a564bbc1f3.mp3" }, { "id": "emo_Amusement-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-1", "key": "3667858480570da6b954e12f9d95f5e7484f86013cab2f228e02049776baad7c", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I found the little box.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It was beside the old window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "991171f2b8e5faac0063c6825862cd63691ff92bba94354e074aba2118ee000e", "generation_seconds_batch": 17.316926753963344, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2943968772888184, "target_z": 2.093749901249186, "ce": 6.165581703186035, "genuineness": 3.9550557136535645, "identity": 0.5808173418045044, "hypothesis": "I found little box. It was beside the old window. We can look inside together.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/3667858480570da6b954e12f9d95f5e7484f86013cab2f228e02049776baad7c.mp3" }, { "id": "emo_Amusement-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-0", "key": "3670aac43a50b055c647a4af94a4dcfa03650766f19463bea83900256ba02f49", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "b425b219c3ebd0ccf98ae626a87901fab6707fc517f1190c14ef0d872e238132", "generation_seconds_batch": 22.295171356992796, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.484196424484253, "target_z": 2.3124998196724262, "ce": 6.0305562019348145, "genuineness": 3.6287014484405518, "identity": 0.3711191713809967, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/3670aac43a50b055c647a4af94a4dcfa03650766f19463bea83900256ba02f49.mp3" }, { "id": "emo_Amusement-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-0", "key": "36bdf58814e0268c2f0e7fe8cef0ec4bb22039554adf6a204ee6fa5e61b52474", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "6182e18f924b5b7b6ca35724bd9ebe48ec8011484846edcfe82dfb857ed47217", "generation_seconds_batch": 25.29698006203398, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6572126150131226, "target_z": 1.3593750966040574, "ce": 5.974957466125488, "genuineness": 3.6287014484405518, "identity": 0.4063681960105896, "hypothesis": "La puerta sigue abierta, he dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/36bdf58814e0268c2f0e7fe8cef0ec4bb22039554adf6a204ee6fa5e61b52474.mp3" }, { "id": "emo_Amusement-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-1", "key": "36c4011d7e0416c52a670a85ca84fcda87a7c4755827d60e30894ef03f033e9b", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I found the little box.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It was beside the old window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "aab47d01aadd5c0e41a44a85697c770db2d3d141dd184cf115ea7d4c7a394907", "generation_seconds_batch": 21.45707138394937, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.226611375808716, "target_z": 2.015624989266216, "ce": 6.284721851348877, "genuineness": 4.3504462242126465, "identity": 0.534349799156189, "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_Amusement/36c4011d7e0416c52a670a85ca84fcda87a7c4755827d60e30894ef03f033e9b.mp3" }, { "id": "emo_Amusement-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-0", "key": "37794ce2de162c68fe1953f1a34512e41e2a3175c800fc87d95488183a05d3a5", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "73344ed71b23afa9a7c384a44c65b32857fe049f398f3c15868d8e4c0f355d6d", "generation_seconds_batch": 16.488341031013988, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.267282724380493, "target_z": 2.0624999914129725, "ce": 5.927301406860352, "genuineness": 3.9927117824554443, "identity": 0.4538615643978119, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/37794ce2de162c68fe1953f1a34512e41e2a3175c800fc87d95488183a05d3a5.mp3" }, { "id": "emo_Amusement-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-0", "key": "3783a546912f24bcb7dc2e52fc0279074bb375fb6a8c7e7fdd2890a7f7faf798", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De deur staat nog open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "49d78cd8ab7011497a166015b4d0bc742f1eacae8d3c618ba6bcff93d44ca348", "generation_seconds_batch": 22.449645560933277, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.240168571472168, "target_z": 2.0312500815767596, "ce": 6.24500846862793, "genuineness": 4.457139015197754, "identity": 0.6307930946350098, "hypothesis": "De deur 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_Amusement/3783a546912f24bcb7dc2e52fc0279074bb375fb6a8c7e7fdd2890a7f7faf798.mp3" }, { "id": "emo_Amusement-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-0", "key": "37baf7312dbf55bd9a4d17aa19e0cf496ae425f1b21ce0f57879e3f122b34e95", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The door is still open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "605a9403f1679c8cdb4000e3f77c54428950844b645834f2c4494e7cde5eb844", "generation_seconds_batch": 25.69331979297567, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8266764879226685, "target_z": 1.5546875139539194, "ce": 6.252951145172119, "genuineness": 4.143336772918701, "identity": 0.27666282653808594, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/37baf7312dbf55bd9a4d17aa19e0cf496ae425f1b21ce0f57879e3f122b34e95.mp3" }, { "id": "emo_Amusement-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-0", "key": "37f62382320b84f8b9a02348010a09d52291c0ebe86a453aed8117b5207fa974", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "b081fc9e6a03db4fc8c27662dc8ff2dde7f577ee4a45db114c3513edaf285534", "generation_seconds_batch": 21.91472171503119, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.192718505859375, "target_z": 1.9765623958822938, "ce": 6.308549880981445, "genuineness": 4.2249250411987305, "identity": 0.37159863114356995, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/37f62382320b84f8b9a02348010a09d52291c0ebe86a453aed8117b5207fa974.mp3" }, { "id": "emo_Amusement-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-1", "key": "3814faa6a1c1545c6016de958e175e9b6b1754fe36e853d044d85a77791a6ad0", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "caf3f37b51fb984edb76ee3e2208378a553afda880cf69c4c06086803574781a", "generation_seconds_batch": 22.901089824037626, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0810351371765137, "target_z": 0.6953125203941899, "ce": 6.2767791748046875, "genuineness": 4.331617832183838, "identity": 0.5651215314865112, "hypothesis": "J'ai trouvé la 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_Amusement/3814faa6a1c1545c6016de958e175e9b6b1754fe36e853d044d85a77791a6ad0.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": "384771d16b59d97c476112c8740a3758d5f1a12650c64c57584998dd74f3a1db", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3f0ec8b797ac33b34cffa15cc54ac3c176e7ed945a5a226ba11ac4185bb5da40", "generation_seconds_batch": 21.25579543202184, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3215112686157227, "target_z": 2.125000085870273, "ce": 6.09409761428833, "genuineness": 3.9927117824554443, "identity": 0.5786750912666321, "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_Amusement/384771d16b59d97c476112c8740a3758d5f1a12650c64c57584998dd74f3a1db.mp3" }, { "id": "emo_Amusement-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-1", "key": "386b4afa0df7b80ef8ffdfc0ea96d8ed0b6d10cd119342a41698899cad7673da", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b709a29ed2221b0f1caeb0f465d33e3ca210b76edb41c9a414baa79cd432f3c8", "generation_seconds_batch": 24.223225228022784, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4674129486083984, "target_z": 1.1406250407883798, "ce": 6.459460258483887, "genuineness": 4.005263805389404, "identity": 0.5335448980331421, "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_Amusement/386b4afa0df7b80ef8ffdfc0ea96d8ed0b6d10cd119342a41698899cad7673da.mp3" }, { "id": "emo_Amusement-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-0", "key": "38f14c6ca11f1b03358123f6f8c649b97e02ae14bb8c13b2c410044d397eb4e3", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De deur staat nog open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "0d7a2c875edfa95d71395374a57893815e7bb0225b8263518853cc719e1ee6bd", "generation_seconds_batch": 23.534630861948244, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1420421600341797, "target_z": 0.7656250236143252, "ce": 6.24500846862793, "genuineness": 4.400654315948486, "identity": 0.7125659584999084, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/38f14c6ca11f1b03358123f6f8c649b97e02ae14bb8c13b2c410044d397eb4e3.mp3" }, { "id": "emo_Amusement-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-1", "key": "391d83841ff8271c671bd38883f08b5179d09ed71daad8d793f1c2e2d9cea822", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "9cfa7d9f4b38bb1e6a2f12ffdc742907f295004a0a953cfdabb6f628f3308d8d", "generation_seconds_batch": 19.191239706007764, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6978839635849, "target_z": 1.4062500987508142, "ce": 6.443574905395508, "genuineness": 4.162164688110352, "identity": 0.3753162622451782, "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_Amusement/391d83841ff8271c671bd38883f08b5179d09ed71daad8d793f1c2e2d9cea822.mp3" }, { "id": "emo_Amusement-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-0", "key": "3962338fc6f1888b9c71a3396dec167ad96b378eab2965a3caa51d9794081b76", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "102102272f01a4d3494113bf5518cf142e329e3b2639f3820bb58cb291129578", "generation_seconds_batch": 16.91480943595525, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.426741600036621, "target_z": 1.093750038641623, "ce": 6.23706579208374, "genuineness": 4.13078498840332, "identity": 0.7092468738555908, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/3962338fc6f1888b9c71a3396dec167ad96b378eab2965a3caa51d9794081b76.mp3" }, { "id": "emo_Amusement-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-0", "key": "396602de1b607892267cf87566ec73e6ea5aec14ee7076b9269557b736ae57bd", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "89ffb92856dbe2cabb24c72ac7a62a37d5a6d8f9c38b38fd0aedbcba4323c1b3", "generation_seconds_batch": 24.35164685593918, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4164109230041504, "target_z": 2.2343749076894563, "ce": 6.157639026641846, "genuineness": 4.3504462242126465, "identity": 0.655547559261322, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/396602de1b607892267cf87566ec73e6ea5aec14ee7076b9269557b736ae57bd.mp3" }, { "id": "emo_Amusement-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-1", "key": "3985b8efdb3c3a7cb483e6a9e994af6c3041706b23e2d2fbdf6ab5b88b9ee973", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "5915306b4f9fda96b39cf48d812bf22c2cfa1a9f314c4ac6cfe635098be957f2", "generation_seconds_batch": 22.134898493997753, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6165412664413452, "target_z": 1.3125000944573006, "ce": 6.4912309646606445, "genuineness": 4.344170093536377, "identity": 0.4374702572822571, "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_Amusement/3985b8efdb3c3a7cb483e6a9e994af6c3041706b23e2d2fbdf6ab5b88b9ee973.mp3" }, { "id": "emo_Amusement-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-0", "key": "39cd299ab05624e16c8e8dba6ad964cfa646dfc774b9191aebae02499eca7ec6", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "214b1ddabbdee567089b8e305faad8c27ba029db54f9b16346465b17257130d0", "generation_seconds_batch": 16.934897080995142, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8809049129486084, "target_z": 1.6171874710187828, "ce": 6.213237762451172, "genuineness": 4.13078498840332, "identity": 0.3304414749145508, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/39cd299ab05624e16c8e8dba6ad964cfa646dfc774b9191aebae02499eca7ec6.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": "3a0a0b9e01e352863f6e860d162eec99e122a430cf04be8b550229b3e916b054", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cb38f8a833829f9762181cffaf61df7a0c5fdcee64821e0bcfbd5bcd1a98501a", "generation_seconds_batch": 20.120428815949708, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6436554193496704, "target_z": 1.3437500042935138, "ce": 6.1894097328186035, "genuineness": 4.557555198669434, "identity": 0.6949890851974487, "hypothesis": "J'ai écrit le numéro sur l'enveloppe, lis le bien et vérifie les deux derniers chiffres. Appelle-moi quand you're a moment.", "wer": 0.13636363636363635, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/3a0a0b9e01e352863f6e860d162eec99e122a430cf04be8b550229b3e916b054.mp3" }, { "id": "emo_Amusement-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-1", "key": "3aca1c2e9efc361e39248f7a67e4e585a087cf4f92e23e98b7d8f2b0835e8cdc", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "d5718b0e9464c1cc3d84b2ba8031525deca0294b3e905212006d9f275e8ca206", "generation_seconds_batch": 23.8819565520389, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.5958800315856934, "target_z": 3.5937499699454043, "ce": 5.998785495758057, "genuineness": 4.149612903594971, "identity": 0.6420466899871826, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/3aca1c2e9efc361e39248f7a67e4e585a087cf4f92e23e98b7d8f2b0835e8cdc.mp3" }, { "id": "emo_Amusement-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-1", "key": "3b54e49ed49a7285095a5c1341722d47c2a79382e8a8ef22a08899fc10e54a0c", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "abae99f48affd52f1dde3d513dd26ef66340d830ca4274f882a0287bbd0ab26e", "generation_seconds_batch": 18.047275956952944, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6165412664413452, "target_z": 1.3125000944573006, "ce": 6.475345611572266, "genuineness": 3.9927117824554443, "identity": 0.5735218524932861, "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_Amusement/3b54e49ed49a7285095a5c1341722d47c2a79382e8a8ef22a08899fc10e54a0c.mp3" }, { "id": "emo_Amusement-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-0", "key": "3bb6fb2fb02d7038e50fcffdc6766d509a042f11527840e61c01e2d8baf24a17", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "270c3b2e2bc2dd3df27f0d49820d93ccb23002844972cab55e0aa1541de15618", "generation_seconds_batch": 23.445438673952594, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.724998116493225, "target_z": 1.4375000085870273, "ce": 6.292664527893066, "genuineness": 4.557555198669434, "identity": 0.6807390451431274, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/3bb6fb2fb02d7038e50fcffdc6766d509a042f11527840e61c01e2d8baf24a17.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": "3bc771e0fc25a2eed84fbdd0e0ce2b2838fcc7774c0ea4363e1742b64b8cf32a", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3483ac7e6eec10c78d132ea53dcc2312ff870b3ea60d1887b33649cef3a54413", "generation_seconds_batch": 17.906031823018566, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.426741600036621, "target_z": 1.093750038641623, "ce": 6.054384231567383, "genuineness": 4.344170093536377, "identity": 0.6638109087944031, "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_Amusement/3bc771e0fc25a2eed84fbdd0e0ce2b2838fcc7774c0ea4363e1742b64b8cf32a.mp3" }, { "id": "emo_Amusement-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-0", "key": "3bed08f4a77f00a8fefafc119d2150af87498c8d423b3ab0c4dba3a69ea6c076", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "390eb521900fb78a44a76050cd3163a13b35256ee5d66151755e84e795543409", "generation_seconds_batch": 17.867182562011294, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4164109230041504, "target_z": 2.2343749076894563, "ce": 5.784333229064941, "genuineness": 3.835810661315918, "identity": 0.6053820848464966, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/3bed08f4a77f00a8fefafc119d2150af87498c8d423b3ab0c4dba3a69ea6c076.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_Amusement", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": "fa866f2ff08494f7577b159600265b036c75c83d6124dec744e44a77605e5a66", "generation_seconds_batch": 16.512283504009247, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.419963002204895, "target_z": 1.0859374924863512, "ce": 6.173524379730225, "genuineness": 4.413206577301025, "identity": 0.4884538948535919, "hypothesis": "De sleutels liggen vond op een keukentafel. Ik keek in de la en daarna naast het raam. Neem ze mee als je weggaat.", "wer": 0.09090909090909091, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/3c590f9302048ad206a88d3c2440f1028cc9eea1f1662250baf365be21a6ebfa.mp3" }, { "id": "emo_Amusement-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-1", "key": "3ce506005b07a749e19d64833882c0f7a8ab17625601ce032c387cb2d04e9192", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "f1dd7404e5ec65d7c0d2668091ad710a04330723eb648645913909114d59df95", "generation_seconds_batch": 23.55016153305769, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8809049129486084, "target_z": 1.6171874710187828, "ce": 6.197352409362793, "genuineness": 4.381826400756836, "identity": 0.6142222881317139, "hypothesis": "J'ai trouvé la 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_Amusement/3ce506005b07a749e19d64833882c0f7a8ab17625601ce032c387cb2d04e9192.mp3" }, { "id": "emo_Amusement-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-0", "key": "3dbdd2180cf3ab98caf130e1a6b3f4a98dc5261d4704bf407a12920022e87abe", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The door is still open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "a91af305b998c6fc30d8aea4b5c979cd9cc9e527dd5ec7343feb120ff3f0a5c5", "generation_seconds_batch": 24.669070275966078, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.938685417175293, "target_z": 0.531250012880541, "ce": 6.213237762451172, "genuineness": 4.005263805389404, "identity": 0.4439643323421478, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/3dbdd2180cf3ab98caf130e1a6b3f4a98dc5261d4704bf407a12920022e87abe.mp3" }, { "id": "emo_Amusement-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-0", "key": "3e0338247c3c431243bb7c89b9031f8d0cf76fb93cd5adb3e49457c9187835f3", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The door is still open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "87fe9ff3ce7b3d7b0b41c8023813272f75bc060398dadbd6ca9dbb3cdb26604d", "generation_seconds_batch": 16.07988484890666, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2808399200439453, "target_z": 2.0781250837235166, "ce": 6.173524379730225, "genuineness": 3.515732765197754, "identity": 0.32030242681503296, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/3e0338247c3c431243bb7c89b9031f8d0cf76fb93cd5adb3e49457c9187835f3.mp3" }, { "id": "emo_Amusement-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-0", "key": "3ee7a99d8af38ba83e75c2c3d6723e9f1fcdbdae91b63f1359aa8a616acdc08e", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "b550fee088c69031cc29b37f023cefb572b5be91f6303809bf881cd2941f6155", "generation_seconds_batch": 21.838790362002328, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3215112686157227, "target_z": 2.125000085870273, "ce": 6.173524379730225, "genuineness": 4.469690799713135, "identity": 0.48743703961372375, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/3ee7a99d8af38ba83e75c2c3d6723e9f1fcdbdae91b63f1359aa8a616acdc08e.mp3" }, { "id": "emo_Amusement-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-0", "key": "3ee9d2bf2394b8705d7828c114c992e6044ce617fc790cc3f56c9ccdf132b3a2", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De deur staat nog open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "5611092dc8503077a2a088f7f429c74d55e6be4b65d1eed07b4255c42192070c", "generation_seconds_batch": 22.93507560098078, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1420421600341797, "target_z": 0.7656250236143252, "ce": 6.117925643920898, "genuineness": 4.344170093536377, "identity": 0.6652117967605591, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/3ee9d2bf2394b8705d7828c114c992e6044ce617fc790cc3f56c9ccdf132b3a2.mp3" }, { "id": "emo_Amusement-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-1", "key": "3ef3ade6f17a40f1111bd8069babea6e6fc65538d2d0a877d3c0cd8b99743810", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "c148d1353a1d0accc322d2381f2c45f7fff482925d5343e8f77fabee875ce046", "generation_seconds_batch": 23.649470258969814, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.619767665863037, "target_z": 2.4687499184232404, "ce": 6.348263263702393, "genuineness": 3.7040140628814697, "identity": 0.36239251494407654, "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_Amusement/3ef3ade6f17a40f1111bd8069babea6e6fc65538d2d0a877d3c0cd8b99743810.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": "3f6f311e80988da75f0de053158705ef69c0597e305ef8648a62d8c03ab487ef", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1ec588cd91e4a0e00de12a150e4aeca24af3eef3c6b2435a60354cd52a260cff", "generation_seconds_batch": 20.106202461058274, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0029189586639404, "target_z": 1.7578124774590533, "ce": 6.173524379730225, "genuineness": 4.532451152801514, "identity": 0.4951685070991516, "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_Amusement/3f6f311e80988da75f0de053158705ef69c0597e305ef8648a62d8c03ab487ef.mp3" }, { "id": "emo_Amusement-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-0", "key": "3f73c50428b8268ad5beb4b21a7dcb77417afbdb68a17c13332ac0341b97ed41", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De deur staat nog open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "2273b2daf51af19c14883b7191042ef45b5c5785dbf14c191ff996562b9b93b2", "generation_seconds_batch": 24.15502780303359, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.240168571472168, "target_z": 2.0312500815767596, "ce": 5.895530700683594, "genuineness": 4.2249250411987305, "identity": 0.1467818319797516, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/3f73c50428b8268ad5beb4b21a7dcb77417afbdb68a17c13332ac0341b97ed41.mp3" }, { "id": "emo_Amusement-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-0", "key": "3fea80c43ef6951deb355bd18dfae13478475ac9225779a45d9520715abba56a", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "9d82a7fc4ce5b1fc1f1b18dab1432e53828f05b2166cd1520dfdfbb0f78254fc", "generation_seconds_batch": 23.617233429918997, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5655391216278076, "target_z": 2.40624982396594, "ce": 5.847874641418457, "genuineness": 3.735394239425659, "identity": 0.5294296741485596, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/3fea80c43ef6951deb355bd18dfae13478475ac9225779a45d9520715abba56a.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": "3fea8a11c28a2f29f246547f49a316073c343879170637ec950a5d6d0ed5ca56", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "72d3b95e4b5afdb3c015b69c316229f0dd84b393667449ddb94ce8307bff8022", "generation_seconds_batch": 20.43811117298901, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8673478364944458, "target_z": 1.6015625161006761, "ce": 6.157639026641846, "genuineness": 4.362998008728027, "identity": 0.5372974872589111, "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_Amusement/3fea8a11c28a2f29f246547f49a316073c343879170637ec950a5d6d0ed5ca56.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": "404bd54ad67b4af7aca4af9b33b726ed3d626ee831dbb367d95f27e05b7544ad", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "85a4bc3be3822a9db78a0ef425f66d579cae3023285e937bf445a30051ef5499", "generation_seconds_batch": 20.169260118040256, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9215762615203857, "target_z": 1.6640624731655396, "ce": 6.086154937744141, "genuineness": 4.281409740447998, "identity": 0.5610374808311462, "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_Amusement/404bd54ad67b4af7aca4af9b33b726ed3d626ee831dbb367d95f27e05b7544ad.mp3" }, { "id": "emo_Amusement-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-1", "key": "40940558834e798cc7dfda9a318f9554e575529ecfdad87178ee4845a0e2cba3", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c7dd60765a77bc49ddc436cf85400572eee1ba91791ace8121dc850e9d9be041", "generation_seconds_batch": 24.859540752018802, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4299681186676025, "target_z": 2.25, "ce": 6.229123115539551, "genuineness": 4.111956596374512, "identity": 0.29250994324684143, "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_Amusement/40940558834e798cc7dfda9a318f9554e575529ecfdad87178ee4845a0e2cba3.mp3" }, { "id": "emo_Amusement-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-0", "key": "4096059758f3299952ca551203598e44823cd8c8eef59ebc7b2f00a67b57e777", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The door is still open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "46bede448f85d41e5a2e5a810b3ac6d0ab27c371df7d11704978edb4a60a8b89", "generation_seconds_batch": 23.580510433996096, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.497753620147705, "target_z": 2.32812491198297, "ce": 6.054384231567383, "genuineness": 3.6412534713745117, "identity": 0.44122210144996643, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/4096059758f3299952ca551203598e44823cd8c8eef59ebc7b2f00a67b57e777.mp3" }, { "id": "emo_Amusement-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-1", "key": "40d48236a63dcad319cf3d9e6cfa76fd2ceec66fc8883832a7bb8262396e53ca", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "6715714a445d353c6052bcbf7a516e6a81cc3dfdcb03e5f86ce04aee4148c1d2", "generation_seconds_batch": 23.628680750960484, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.267282724380493, "target_z": 2.0624999914129725, "ce": 6.086154937744141, "genuineness": 4.068024158477783, "identity": 0.658474326133728, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana, vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/40d48236a63dcad319cf3d9e6cfa76fd2ceec66fc8883832a7bb8262396e53ca.mp3" }, { "id": "emo_Amusement-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-1", "key": "40f0988ef04ff0619adfd4acac1be20e3f338e7a68d3b740b191fc7cbe9b6fad", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "b6b90ed8999b99d8dbaa26443fd54836ae7a2e1fc4fe67edb12ec6ac3569a488", "generation_seconds_batch": 18.20235988101922, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9180243015289307, "target_z": 2.812500025761082, "ce": 5.998785495758057, "genuineness": 4.3504462242126465, "identity": 0.007126333191990852, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/40f0988ef04ff0619adfd4acac1be20e3f338e7a68d3b740b191fc7cbe9b6fad.mp3" }, { "id": "emo_Amusement-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-1", "key": "4152c6c51f4cccde78d113761688a45c5b2ccc91150ac0bd1389e7efc255ac79", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "b2bedf3ddaedebeea4a427e6bc9a7876a0bd9d2f40b76c5115efd81257fa44e1", "generation_seconds_batch": 24.225773444981314, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7792266607284546, "target_z": 1.500000103044328, "ce": 6.24500846862793, "genuineness": 4.419482707977295, "identity": 0.722676157951355, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/4152c6c51f4cccde78d113761688a45c5b2ccc91150ac0bd1389e7efc255ac79.mp3" }, { "id": "emo_Amusement-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-1", "key": "41724303e5b3363f45290bad615cbc8ebce57ce517189bf8b6bbc02e63171718", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "42e20a17486ae16af3ff37e2a13bc2d1e9cff22a58436b27ebf4249a424d5b46", "generation_seconds_batch": 21.879918935941532, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7860051393508911, "target_z": 1.5078125118071626, "ce": 6.475345611572266, "genuineness": 4.21237325668335, "identity": 0.5260155200958252, "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_Amusement/41724303e5b3363f45290bad615cbc8ebce57ce517189bf8b6bbc02e63171718.mp3" }, { "id": "emo_Amusement-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-1", "key": "419bda2622e9c23566247e0c4da68c20030dc6dfa05a3aa16f961583230f35ab", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I found the little box.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It was beside the old window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "47f4e55d1d9cc5a5d8c436a5a1958c65f5d7a32a1f6ef05c809c544ff8bed6eb", "generation_seconds_batch": 23.549201735993847, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.08070969581604, "target_z": 3.0000000343481092, "ce": 6.046441555023193, "genuineness": 3.8797430992126465, "identity": 0.5378277897834778, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/419bda2622e9c23566247e0c4da68c20030dc6dfa05a3aa16f961583230f35ab.mp3" }, { "id": "emo_Amusement-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-1", "key": "41a2fbbf144861ba348fc3c791ee0c10961bc75e60b9dbad5e737de0a2785e0d", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "7d3c2ba2850ce8ff5600cf33a7690e61329b7326a23835dfeedfe5f82c475d1c", "generation_seconds_batch": 25.62727267097216, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5623127222061157, "target_z": 1.25, "ce": 6.141753673553467, "genuineness": 4.570107460021973, "identity": 0.6560708284378052, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja y podemos mirar juntos lo que hay dentro.", "wer": 0.058823529411764705, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/41a2fbbf144861ba348fc3c791ee0c10961bc75e60b9dbad5e737de0a2785e0d.mp3" }, { "id": "emo_Amusement-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-1", "key": "42b9d1a417bde724ae2621046d95be576fa5c4bf04aff971972f70e70039dce3", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "a29dbb48e2704c5bdf4a34e7b0abec44d899427b8f05fc66938c3857adf360a8", "generation_seconds_batch": 23.57856297097169, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5248677730560303, "target_z": 2.3593748218191832, "ce": 5.677107334136963, "genuineness": 3.9173994064331055, "identity": 0.1681656539440155, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/42b9d1a417bde724ae2621046d95be576fa5c4bf04aff971972f70e70039dce3.mp3" }, { "id": "emo_Amusement-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-0", "key": "42bd5c6f4427c8c375dd0fbabdfe205d06f6e1b6fd3db37b84e1dbee67eea3fd", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9d875b67d50b5da2d067783b5f8907f5c0d89c6683b8ef115f7f93664c50b664", "generation_seconds_batch": 23.280330864945427, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4299681186676025, "target_z": 2.25, "ce": 6.260893821716309, "genuineness": 4.406930446624756, "identity": 0.634705126285553, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/42bd5c6f4427c8c375dd0fbabdfe205d06f6e1b6fd3db37b84e1dbee67eea3fd.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": "42c8091594b0dec4f21db7ec68fca9857493a9fabb6b98abd4f39d524d8f5374", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fd5f684b9d1ece88e2d3be5b59b21a40858cc79c114c2e4fac363d330fa75327", "generation_seconds_batch": 19.123501325957477, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2098276615142822, "target_z": 0.843749935597295, "ce": 6.316492557525635, "genuineness": 4.6203155517578125, "identity": 0.6229831576347351, "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_Amusement/42c8091594b0dec4f21db7ec68fca9857493a9fabb6b98abd4f39d524d8f5374.mp3" }, { "id": "emo_Amusement-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-0", "key": "4304b66ad010b9cbfd1892d5f35e1c9376bfda5509e89099b229b66987d2bd08", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The door is still open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "379af4b3ed85f768a04eeb785c7f23f7e223b7d42c6e8e204695e988309cb69f", "generation_seconds_batch": 24.782631139969453, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0639259815216064, "target_z": 1.8281249806791886, "ce": 6.372091293334961, "genuineness": 3.9927117824554443, "identity": 0.3562904894351959, "hypothesis": "The 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_Amusement/4304b66ad010b9cbfd1892d5f35e1c9376bfda5509e89099b229b66987d2bd08.mp3" }, { "id": "emo_Amusement-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-1", "key": "430cca65bb68b97931f22394517789f13b9c9d0f7f3f24ccb7f1170325236743", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "53066ab2b901d216eeb0025b882b89ffc4f46effe5c615a1040b0297c477a9fe", "generation_seconds_batch": 24.564030235051177, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1520471572875977, "target_z": 1.9296873937355368, "ce": 6.173524379730225, "genuineness": 4.068024158477783, "identity": 0.6627950668334961, "hypothesis": "J'ai trouvé la 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_Amusement/430cca65bb68b97931f22394517789f13b9c9d0f7f3f24ccb7f1170325236743.mp3" }, { "id": "emo_Amusement-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-1", "key": "431b4d937289aaa64124b2a4b5e8f06c9be6aca5cd8016b8e6f34c8613a162df", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bcc91b4a2830ad7b28b56820d3d5dc1e225bb4dc37fc2663e631045d4d6c5ca8", "generation_seconds_batch": 24.344563807942905, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8809049129486084, "target_z": 1.6171874710187828, "ce": 6.4515180587768555, "genuineness": 4.017816066741943, "identity": 0.6210424900054932, "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_Amusement/431b4d937289aaa64124b2a4b5e8f06c9be6aca5cd8016b8e6f34c8613a162df.mp3" }, { "id": "emo_Amusement-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-1", "key": "432b011588f018633525b069ada8e1e8591a8b54f16de42b461dd97f58951fe1", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "0b0b5ab436c46fc6bc6dabf94a7456a145c9f300d675db5892188d94c9e8b347", "generation_seconds_batch": 21.260337637970224, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8537907600402832, "target_z": 1.5859375611825697, "ce": 6.523001670837402, "genuineness": 4.055472373962402, "identity": 0.5305917859077454, "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_Amusement/432b011588f018633525b069ada8e1e8591a8b54f16de42b461dd97f58951fe1.mp3" }, { "id": "emo_Amusement-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-1", "key": "434132dbd54940ad5d5c1d3da64267b59b6f7ff146c7243cae32bfc64796ebce", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "973c0473ed473ddd0f2a54e97810cd96323c94434685a89d8906ecc9e780506c", "generation_seconds_batch": 23.361566098988988, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0503687858581543, "target_z": 1.8124998883686447, "ce": 6.0146708488464355, "genuineness": 3.9927117824554443, "identity": 0.5942447185516357, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/434132dbd54940ad5d5c1d3da64267b59b6f7ff146c7243cae32bfc64796ebce.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_Amusement", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": "dc59daac7d51b19b534350de6d0724a216699869117508df2c1b335e60e4bd78", "generation_seconds_batch": 18.52951063401997, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8741264343261719, "target_z": 1.6093750622559482, "ce": 6.09409761428833, "genuineness": 4.3127899169921875, "identity": 0.6519997715950012, "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_Amusement/434f953004ee3838b31e4f505ba0cb9202b34ab37936979fff50edb64a6a996f.mp3" }, { "id": "emo_Amusement-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-1", "key": "437a398fb6948d1136cc1f5e4bffed07ce4c5364eeea126c492e9915c8b2bf3f", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I found the little box.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It was beside the old window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1b6b2ce4519aafd3e43fa15bce0766143829abcc5bf8d3f91075ecff91b0c737", "generation_seconds_batch": 18.33543976699002, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.823124408721924, "target_z": 2.7031249291570245, "ce": 6.41180419921875, "genuineness": 4.036643981933594, "identity": 0.25504547357559204, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/437a398fb6948d1136cc1f5e4bffed07ce4c5364eeea126c492e9915c8b2bf3f.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_Amusement", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2e9949af9f32345820fe1ee6ff6c2628b4aeda48e3ca180666ecd035d175e59b", "generation_seconds_batch": 17.837927926098928, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.33624106645584106, "target_z": -0.16308595641829457, "ce": 6.268836498260498, "genuineness": 4.6203155517578125, "identity": 0.6993957161903381, "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_Amusement/43d771a5c055e2aea1186dc99f4cdef2b4c6bc8c6b2779ad35a29ca11c75a91c.mp3" }, { "id": "emo_Amusement-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-1", "key": "4430a26a64f28578ee792761b690ecdceadbbf5070112912afd5b8c71f0abbd1", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "4ffde4234a0b3c6089a9c8a3511577d79686ba1719fccc4b41df4f785186a99a", "generation_seconds_batch": 25.251025289064273, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.243720531463623, "target_z": 0.8828125289812172, "ce": 6.141753673553467, "genuineness": 4.256305694580078, "identity": 0.6522742509841919, "hypothesis": "J'ai trouvé la 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_Amusement/4430a26a64f28578ee792761b690ecdceadbbf5070112912afd5b8c71f0abbd1.mp3" }, { "id": "emo_Amusement-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-0", "key": "4468e099b719a34bf576461b1d32f923b045b3de285e39e9c6bc209ee41c79fe", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "114183cac3eeec0501333b97f063d0faec09b1d8456f3dbbc82726926e68c728", "generation_seconds_batch": 24.439315010909922, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.104597330093384, "target_z": 1.8749999828259454, "ce": 6.38003396987915, "genuineness": 4.3127899169921875, "identity": 0.5639573335647583, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/4468e099b719a34bf576461b1d32f923b045b3de285e39e9c6bc209ee41c79fe.mp3" }, { "id": "emo_Amusement-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-1", "key": "44bd9579b2604b90433bd8b23f2672f264a8781f694f4550d31779804eaf6f41", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "a2ee8686ba08c364dacb701bf0593e6574c2ee8d4b7c6e0696182d7e353098e7", "generation_seconds_batch": 25.689211406977847, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7824530601501465, "target_z": 2.656249927010268, "ce": 6.062326908111572, "genuineness": 4.300237655639648, "identity": 0.7615381479263306, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/44bd9579b2604b90433bd8b23f2672f264a8781f694f4550d31779804eaf6f41.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": "44d3401b306c53a1ae6dbdb42aa7d001e75ac91c20f671ac9ff0db754e286529", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Someone moved the little blue chair.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4b59fb206072d586fa8c38400a55ff6497812d8ff92118081968dd89e8b2d1b3", "generation_seconds_batch": 16.736577088944614, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3792916536331177, "target_z": 1.0390624903395942, "ce": 6.348263263702393, "genuineness": 4.413206577301025, "identity": 0.381232887506485, "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_Amusement/44d3401b306c53a1ae6dbdb42aa7d001e75ac91c20f671ac9ff0db754e286529.mp3" }, { "id": "emo_Amusement-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-1", "key": "4500557a13199b250c9e0a59bcf7ba4de4b56b3ef70a5059de7ece33fea7355e", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "eaa948f2837fcfb209eeb0433fb8e50a77d8e36f0c9a88ca38ed6f3eb0be5150", "generation_seconds_batch": 18.055171277956106, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.758890986442566, "target_z": 1.4765626019709495, "ce": 6.205295085906982, "genuineness": 4.494794845581055, "identity": 0.7826851010322571, "hypothesis": "J'ai trouvé la 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_Amusement/4500557a13199b250c9e0a59bcf7ba4de4b56b3ef70a5059de7ece33fea7355e.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": "45032e8438a595f6b261bc4235de496417b6fece0c5c3d1a55397a1d5b32d89d", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "89240f4343b2c16f04e087d0885bf6ff9beb02ff47821369ef24e778aac3a947", "generation_seconds_batch": 20.139344363007694, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.05714750289917, "target_z": 1.8203125719163538, "ce": 6.173524379730225, "genuineness": 4.507347106933594, "identity": 0.8045194149017334, "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_Amusement/45032e8438a595f6b261bc4235de496417b6fece0c5c3d1a55397a1d5b32d89d.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": "45a155fb2274e89fc2adb3f467c2f607f9a03b150adc96f7ba1c474a7d6d57d6", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [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": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "f6fa0b995dd3ef8e2c5c3ee6fd3ac981912e9acadfc8a4665a3894ffb9086abf", "generation_seconds_batch": 17.976285106036812, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4570822715759277, "target_z": 2.281249909836213, "ce": 6.292664527893066, "genuineness": 4.124508857727051, "identity": 0.5892572402954102, "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_Amusement/45a155fb2274e89fc2adb3f467c2f607f9a03b150adc96f7ba1c474a7d6d57d6.mp3" }, { "id": "emo_Amusement-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-0", "key": "45e02e12a012820addf3b69866374c16600c7a573d9f0605d590c01908678670", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The door is still open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "5575f5e1cb5d4f7f1ddc3c9e28b23cbc4c2d27ac4dd981fe4939c5a0e3e26e52", "generation_seconds_batch": 15.641851922031492, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.375739574432373, "target_z": 2.1874999055426994, "ce": 5.998785495758057, "genuineness": 3.798154592514038, "identity": 0.49964869022369385, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/45e02e12a012820addf3b69866374c16600c7a573d9f0605d590c01908678670.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_Amusement", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": "92da6baca8a9b3b8dcbddad1ea84ec793029c94576fb22552d735cc753c611b7", "generation_seconds_batch": 17.006485942052677, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3701338768005371, "target_z": -0.12402343173059102, "ce": 6.435632705688477, "genuineness": 4.319066047668457, "identity": 0.5227148532867432, "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_Amusement/45f9ec8497c8691f9e18d794cf98f47c522bfab041b36df5accabf5c5c456412.mp3" }, { "id": "emo_Amusement-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-1", "key": "464c2c0c0a6e7405c50526e86565c01c84aa5b12245dce8f6dd030dd2d84bd0e", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "620c137824399b5e1bfa70e8e297b3dce1292398caab92701bb68b00689047ce", "generation_seconds_batch": 22.906167623004876, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3079540729522705, "target_z": 2.1093749935597295, "ce": 6.292664527893066, "genuineness": 3.773050308227539, "identity": 0.242145836353302, "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_Amusement/464c2c0c0a6e7405c50526e86565c01c84aa5b12245dce8f6dd030dd2d84bd0e.mp3" }, { "id": "emo_Amusement-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-0", "key": "468a5d25267d0f2fb49284fab63e62bb59e5c5772a4cce1899d4dec613cfb522", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "5d05845d39eb39f91b151457de94e589193c7856c2a37f88e4d3d2ae373987ab", "generation_seconds_batch": 22.295171356992796, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5248677730560303, "target_z": 2.3593748218191832, "ce": 5.593709468841553, "genuineness": 3.8169827461242676, "identity": 0.4005610942840576, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/468a5d25267d0f2fb49284fab63e62bb59e5c5772a4cce1899d4dec613cfb522.mp3" }, { "id": "emo_Amusement-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-1", "key": "470a7465b5b43f4403679bb7b933d3c0ec83ee9fe1d6360ee9da7b57af6aefca", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "bb1e82f06ae1fc0412414d66fddf92c244641947d7f9c43c6b8e379293f08101", "generation_seconds_batch": 24.795233883080073, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.962247610092163, "target_z": 1.7109374753122963, "ce": 6.316492557525635, "genuineness": 4.394378662109375, "identity": 0.5717676877975464, "hypothesis": "J'ai trouvé la 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_Amusement/470a7465b5b43f4403679bb7b933d3c0ec83ee9fe1d6360ee9da7b57af6aefca.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": "475f2437ca49943dd1fe148dc8c05f7c97be7e25160668cf3abc0e1079f875d2", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b2beb3c39b68f386aee456e02f3c1136c44548e100b007bbf797c23a7028e83b", "generation_seconds_batch": 20.091444434947334, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.484196424484253, "target_z": 2.3124998196724262, "ce": 6.125868320465088, "genuineness": 4.137060642242432, "identity": 0.6968106031417847, "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_Amusement/475f2437ca49943dd1fe148dc8c05f7c97be7e25160668cf3abc0e1079f875d2.mp3" }, { "id": "emo_Amusement-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-0", "key": "478e19d37ecd08d06014a06a0c045b4bcd7803ecfe343377c9bf95510a9ac897", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5e6c68d570f4e261ec62d188d41d5684f5c225fc5a8740b7562d1f93447a840f", "generation_seconds_batch": 17.612412122893147, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3350682258605957, "target_z": 2.140624903395943, "ce": 6.078212261199951, "genuineness": 4.137060642242432, "identity": 0.6447932720184326, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi, quand tu es prêt?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/478e19d37ecd08d06014a06a0c045b4bcd7803ecfe343377c9bf95510a9ac897.mp3" }, { "id": "emo_Amusement-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-0", "key": "47ab79ec4e4bdbdbe821a80adc932ef82b3beb9d2c59c82fed5f3ffa815c038a", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "7eee9677bf9f18b8d886749bf873f5d02478f18688e4fc70680896747eedad07", "generation_seconds_batch": 17.29784470004961, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1081494092941284, "target_z": 0.7265625676228402, "ce": 6.38003396987915, "genuineness": 4.300237655639648, "identity": 0.5621018409729004, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/47ab79ec4e4bdbdbe821a80adc932ef82b3beb9d2c59c82fed5f3ffa815c038a.mp3" }, { "id": "emo_Amusement-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-0", "key": "47abfec5b92a3321d4aafea6af5f480b2fe201295163621e971662d5e7a7a849", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "7471ab02c06a8915dfa37638e1951dfb076a4ca3a87f1f514088d260a4c229ae", "generation_seconds_batch": 17.402882663998753, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5790963172912598, "target_z": 2.4218749162764834, "ce": 5.95112943649292, "genuineness": 3.4937667846679688, "identity": 0.46650028228759766, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/47abfec5b92a3321d4aafea6af5f480b2fe201295163621e971662d5e7a7a849.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": "47bca9ac14345b139e1b1fcbb65397527d75acb89bb501924e39066beca4928b", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1410b9d0c9a2db7343bf42017202e60cd7af51c7239c85aa07116e0ce9fe0957", "generation_seconds_batch": 29.612505786004476, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8658158779144287, "target_z": 0.44726558823678925, "ce": 6.23706579208374, "genuineness": 4.243753433227539, "identity": 0.5624507665634155, "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_Amusement/47bca9ac14345b139e1b1fcbb65397527d75acb89bb501924e39066beca4928b.mp3" }, { "id": "emo_Amusement-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-1", "key": "47c49c35e3913d3f5d9deb443b8cb6462fac19b3d2663517f5b258097460c4a6", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I found the little box.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It was beside the old window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "3709fd858a556be8e939c4dd64530fc7e6a079f707193468db9128721a434140", "generation_seconds_batch": 23.9244308170164, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2943968772888184, "target_z": 2.093749901249186, "ce": 6.229123115539551, "genuineness": 4.042920112609863, "identity": 0.3979913592338562, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/47c49c35e3913d3f5d9deb443b8cb6462fac19b3d2663517f5b258097460c4a6.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_Amusement", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": "ac2b0b3abca13ea641d4a807188836590a85f0e799d54e550223cf2438b56169", "generation_seconds_batch": 15.490366781014018, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19643333554267883, "target_z": -0.3242187419496619, "ce": 6.046441555023193, "genuineness": 4.268857479095459, "identity": 0.7512311935424805, "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_Amusement/47d00b404f769e82194cfb39f2be7a6bd3cc5bfaac4f38356b0fada2abdb9f4d.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": "480ed00030fbdfefece95820e390aeb37caa51ac51ddf07792cef6d7138572f6", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The road turns left behind the bridge.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7c1cc6d2a4818f3697e61584842a3eba3df41d6b22cf23509e1185145d810214", "generation_seconds_batch": 20.36777614802122, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0640887022018433, "target_z": 0.6757812237022288, "ce": 6.395919322967529, "genuineness": 4.042920112609863, "identity": 0.3500550091266632, "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_Amusement/480ed00030fbdfefece95820e390aeb37caa51ac51ddf07792cef6d7138572f6.mp3" }, { "id": "emo_Amusement-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-1", "key": "482a9beaf8d0348f7b3fe06d09c46b081845abbdcbb64edd9da74150414f8429", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "24e0dbb651a3a4088e69965f6a0b1f053f105c0bd65732e43e7dfaf58aa5d80b", "generation_seconds_batch": 24.464732920052484, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5519821643829346, "target_z": 2.3906250064402705, "ce": 6.252951145172119, "genuineness": 3.465524435043335, "identity": 0.3278028964996338, "hypothesis": "Ich hab die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/482a9beaf8d0348f7b3fe06d09c46b081845abbdcbb64edd9da74150414f8429.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": "4890e3676f0b1d69c4bf1b278a7897c4a6ef417b1cdc237312f0d4e09e1b7de0", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "46dbeadb929e865018e00e0eb8a917ad046d80d964b5597ebc487e5ef15a1f37", "generation_seconds_batch": 16.778751206002198, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6436554193496704, "target_z": 1.3437500042935138, "ce": 6.260893821716309, "genuineness": 4.337893962860107, "identity": 0.7071552276611328, "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_Amusement/4890e3676f0b1d69c4bf1b278a7897c4a6ef417b1cdc237312f0d4e09e1b7de0.mp3" }, { "id": "emo_Amusement-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-0", "key": "491a047700abce27a53319e49ea0b053f950e694ebe11092e706bc71b7b64757", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De deur staat nog open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "1a9fcc8afc8b12bb3b0f6b5fc68646435e4c0c05b6805c0f599b663035c186d8", "generation_seconds_batch": 23.103367885923944, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1723828315734863, "target_z": 1.9531248948089153, "ce": 5.677107334136963, "genuineness": 4.143336772918701, "identity": 0.04051005467772484, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/491a047700abce27a53319e49ea0b053f950e694ebe11092e706bc71b7b64757.mp3" }, { "id": "emo_Amusement-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-1", "key": "49386001f7d2fa9374577df22889570cb0e755f882bb795a18ae8a1d8addbe28", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I found the little box.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It was beside the old window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "220e0758c01c2699a24ebaec31ffb1fd2b313ce750812f3209eceb4461fc3847", "generation_seconds_batch": 21.815514944959432, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.348625421524048, "target_z": 2.1562499957064865, "ce": 6.340320587158203, "genuineness": 3.6977379322052, "identity": 0.25670498609542847, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/49386001f7d2fa9374577df22889570cb0e755f882bb795a18ae8a1d8addbe28.mp3" }, { "id": "emo_Amusement-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-0", "key": "49964067d336393f128e5e4cc39a9246aef7c76cda18ad16d46b3a11ef6cd5d5", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The door is still open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "79ca50f0618dcf2f796772105d6c88a3a21892265ea1aeebe7f1f049634b8c2a", "generation_seconds_batch": 17.79855490999762, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6368769407272339, "target_z": 1.335937595530679, "ce": 6.141753673553467, "genuineness": 3.9550557136535645, "identity": 0.4030555188655853, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/49964067d336393f128e5e4cc39a9246aef7c76cda18ad16d46b3a11ef6cd5d5.mp3" }, { "id": "emo_Amusement-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-1", "key": "49b63bc355dee5f411cc66139d657fb74fc332c987c5690c6db6f3666be84fe1", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "af042eb56afac4c13c934b0e75a1f1bf1a9fe86aa80e6071eab202811b7057c0", "generation_seconds_batch": 21.41946652799379, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3079540729522705, "target_z": 2.1093749935597295, "ce": 6.133810997009277, "genuineness": 4.080576419830322, "identity": 0.4086679518222809, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/49b63bc355dee5f411cc66139d657fb74fc332c987c5690c6db6f3666be84fe1.mp3" }, { "id": "emo_Amusement-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-1", "key": "49c10f97077322e0c5d2c831a64d1329c3b641bb82c3c9c9ef1d9eddae418731", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "209c1cc68aaab85ecb7b21906e3f0b0d09d282ba47fac818ac5689326828b467", "generation_seconds_batch": 24.30096785002388, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4028539657592773, "target_z": 2.218750090163787, "ce": 6.332377910614014, "genuineness": 4.507347106933594, "identity": 0.44053804874420166, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/49c10f97077322e0c5d2c831a64d1329c3b641bb82c3c9c9ef1d9eddae418731.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_Amusement", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": "030daf775c6155158ecf56f05a715fffabdb95b59823d4e6f3af0c3690d4d173", "generation_seconds_batch": 17.586503845988773, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.442156046628952, "target_z": -0.041015626878412224, "ce": 6.038498878479004, "genuineness": 4.143336772918701, "identity": 0.710021436214447, "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_Amusement/49d468ae6540cc7c1e5b0e6883c25e2b29599458c9de0a5398000eaca62677ab.mp3" }, { "id": "emo_Amusement-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-0", "key": "4a3a8a52bc394f9bdde76bc1cbab1e189afd9551e6adf6bf0017f2cafe924cc5", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The door is still open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "3e626dbcb1afd87dc48d431cc6c04c25da6f01ad75204d791eadca35cbc0341f", "generation_seconds_batch": 20.940044949995354, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2943968772888184, "target_z": 2.093749901249186, "ce": 6.197352409362793, "genuineness": 4.18726921081543, "identity": 0.49962902069091797, "hypothesis": "The door's still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.1111111111111111, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/4a3a8a52bc394f9bdde76bc1cbab1e189afd9551e6adf6bf0017f2cafe924cc5.mp3" }, { "id": "emo_Amusement-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-1", "key": "4aa54fad1f79ea7e73e36568a6620f621c67bee213067fe8f3107b21cd966735", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "0cf38ad1372a3a58c048371d14cab136f35e6c3f631d21a79ee5ddd35ec71bef", "generation_seconds_batch": 24.005126739037223, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.084261655807495, "target_z": 1.8515624817525669, "ce": 6.181467056274414, "genuineness": 4.394378662109375, "identity": 0.42273932695388794, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/4aa54fad1f79ea7e73e36568a6620f621c67bee213067fe8f3107b21cd966735.mp3" }, { "id": "emo_Amusement-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-0", "key": "4ad88460f28862352ea15d75bf5d6ad22f9c48e3137aa9af19b2f9d9385704fa", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "db4f836dc6dd2d835f7d14733b9766e71b875741528afb7b532aeeb57bc0f7af", "generation_seconds_batch": 16.689911424997263, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8876835107803345, "target_z": 1.6250000171740546, "ce": 6.252951145172119, "genuineness": 4.143336772918701, "identity": 0.5092200636863708, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/4ad88460f28862352ea15d75bf5d6ad22f9c48e3137aa9af19b2f9d9385704fa.mp3" }, { "id": "emo_Amusement-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-1", "key": "4af3df9e18db202c5d1ce0bf48052b47feef4d68f806dfdc4b75652f48635722", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I found the little box.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It was beside the old window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b159e37587c687cf080432c0291812b20ebde475ce133768a06044c481ca938c", "generation_seconds_batch": 24.69677540997509, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.985809803009033, "target_z": 2.890624937744052, "ce": 6.340320587158203, "genuineness": 3.961331605911255, "identity": 0.3998829126358032, "hypothesis": "I found a little box. It was beside the old window. We can look inside together.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/4af3df9e18db202c5d1ce0bf48052b47feef4d68f806dfdc4b75652f48635722.mp3" }, { "id": "emo_Amusement-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-1", "key": "4c3459eea2f642cb006b7dad4313435aae031a14669bfc8bc51211d897c07f64", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "aa55256a3d843c4cc29af6a2afe03b03ba6d91438b3f33806474091bb3f957ab", "generation_seconds_batch": 25.62727267097216, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8673478364944458, "target_z": 1.6015625161006761, "ce": 6.141753673553467, "genuineness": 4.306513786315918, "identity": 0.716128408908844, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/4c3459eea2f642cb006b7dad4313435aae031a14669bfc8bc51211d897c07f64.mp3" }, { "id": "emo_Amusement-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-1", "key": "4c8240fe1e36d700086d03a05ee73cc6079d0349acda1e6a5b50a61591775e83", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I found the little box.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It was beside the old window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5104de125a1af1e58ad121746618eb451726545de45ff3d118a79aa29b528e0a", "generation_seconds_batch": 21.575124165974557, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7960102558135986, "target_z": 2.6718750193208116, "ce": 6.0146708488464355, "genuineness": 3.6789097785949707, "identity": 0.5137804746627808, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/4c8240fe1e36d700086d03a05ee73cc6079d0349acda1e6a5b50a61591775e83.mp3" }, { "id": "emo_Amusement-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-0", "key": "4d08971a3518aec36229640da4beec2d5ba909023fc036987e4adb8744d1dc24", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The door is still open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "712248dfbc30efd5c60a4230dce59dd6dbf84a7cee4b6f77ad17602472aa48dd", "generation_seconds_batch": 24.18833259504754, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2808399200439453, "target_z": 2.0781250837235166, "ce": 6.070269584655762, "genuineness": 3.427868366241455, "identity": 0.4528498649597168, "hypothesis": "The 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_Amusement/4d08971a3518aec36229640da4beec2d5ba909023fc036987e4adb8744d1dc24.mp3" }, { "id": "emo_Amusement-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-0", "key": "4df2d3f2df36abeaa61c299e8d7379c9853050024f4db78f789b26d1cce29681", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De deur staat nog open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "b65602652aef72620855c992fdf5cf7d9866e7428fe106c003d60ce3a3842a05", "generation_seconds_batch": 18.153017973992974, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2976233959198, "target_z": 3.249999862607563, "ce": 6.141753673553467, "genuineness": 4.250029563903809, "identity": 0.2708808183670044, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/4df2d3f2df36abeaa61c299e8d7379c9853050024f4db78f789b26d1cce29681.mp3" }, { "id": "emo_Amusement-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-0", "key": "4f001e9c677aab747c07411ca62ed692f31a31057b1b83dddd1e107483d629e4", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9b5351888bb410dab078474e92f37cef86f4fa0976013c13655daea989eba0c2", "generation_seconds_batch": 23.102491695899516, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.714667558670044, "target_z": 2.5781250150272976, "ce": 6.229123115539551, "genuineness": 4.469690799713135, "identity": 0.4811081886291504, "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_Amusement/4f001e9c677aab747c07411ca62ed692f31a31057b1b83dddd1e107483d629e4.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": "4f23bcdc4115d60ddd9b1acbb9cb0badf11138062449a728902226529f3b71a4", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0592e35e7ab7644e9e16f0b4fc317c032bb810ddd8dcbefe265b2122a2a114d9", "generation_seconds_batch": 15.970181567943655, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3079540729522705, "target_z": 2.1093749935597295, "ce": 6.3641486167907715, "genuineness": 4.532451152801514, "identity": 0.5729587078094482, "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_Amusement/4f23bcdc4115d60ddd9b1acbb9cb0badf11138062449a728902226529f3b71a4.mp3" }, { "id": "emo_Amusement-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-1", "key": "4f6d5609f3cfbd5df540c42f3295afbdab78a6f37048b231d54672c9e629d226", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "abd488afcdc2a44d8dfccf00ec72ecbd10b6c8bae360db47d126c21a86bc401c", "generation_seconds_batch": 23.195080123026855, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9180243015289307, "target_z": 2.812500025761082, "ce": 6.046441555023193, "genuineness": 4.356721878051758, "identity": 0.4467219412326813, "hypothesis": "J'ai trouvé la 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_Amusement/4f6d5609f3cfbd5df540c42f3295afbdab78a6f37048b231d54672c9e629d226.mp3" }, { "id": "emo_Amusement-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-0", "key": "505ebdba6e2b3b2c8120c9203cbd2c23bce427d765d1c9310c20fb48c746adc7", "bucket": "emo_Amusement", "phase": "wording", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De deur staat nog open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "8218f7a91236dc45c3d618ce1bfddcde34daec92a23474b3003be60541bf1b04", "generation_seconds_batch": 17.25774650007952, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6707696914672852, "target_z": 1.3750000515221639, "ce": 6.054384231567383, "genuineness": 4.293961524963379, "identity": 0.6269233226776123, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/505ebdba6e2b3b2c8120c9203cbd2c23bce427d765d1c9310c20fb48c746adc7.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": "5167f2f21a028b75870b2739270bcb802fd5bc04a7b819ef44e304b550eea61a", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The keys are on the kitchen table.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "289d7914129906692bb4fd2069081cec61ea42916f409764b104dae73125b311", "generation_seconds_batch": 15.301124754012562, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5384249687194824, "target_z": 2.374999914129727, "ce": 6.38003396987915, "genuineness": 4.030367851257324, "identity": 0.1561056673526764, "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_Amusement/5167f2f21a028b75870b2739270bcb802fd5bc04a7b819ef44e304b550eea61a.mp3" }, { "id": "emo_Amusement-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-0", "key": "517290006527be71438ea11dd74526aea577ef711797971ef279dbeb350faebb", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "9804d678ed2ab38f12f4ee870b025396d9c3bf5f9c66c9ad0c057da348293621", "generation_seconds_batch": 25.54260477796197, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0573102235794067, "target_z": 0.6679688149393941, "ce": 6.197352409362793, "genuineness": 4.432034492492676, "identity": 0.7579410076141357, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/517290006527be71438ea11dd74526aea577ef711797971ef279dbeb350faebb.mp3" }, { "id": "emo_Amusement-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-0", "key": "51acb671346dc11ac51608bc46ed97e2d90a1cc2b313ddc1767f0ff654bb4ef4", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The door is still open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "096080ecd68648beb1fd36f330f6865fa3bb7bb80f3cab75e774b67927f975f9", "generation_seconds_batch": 24.52233986801002, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1047600507736206, "target_z": 0.7226562258489857, "ce": 6.205295085906982, "genuineness": 4.036643981933594, "identity": 0.2804107069969177, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/51acb671346dc11ac51608bc46ed97e2d90a1cc2b313ddc1767f0ff654bb4ef4.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": "51b61d9c97770eb63d15b901584dd8bf6f21ec2cb9044eacd46374ddafcbcd82", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "fe6aba9332991efc48aaf11c5b276ecd1d57b77d7328656dca7d5fdecbd79842", "generation_seconds_batch": 20.091444434947334, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.836681604385376, "target_z": 2.718750021467568, "ce": 6.157639026641846, "genuineness": 4.3127899169921875, "identity": 0.33440086245536804, "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_Amusement/51b61d9c97770eb63d15b901584dd8bf6f21ec2cb9044eacd46374ddafcbcd82.mp3" }, { "id": "emo_Amusement-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-1", "key": "52054f5e8a5b7d6b8b702790e1fae6b565970196c7c6e452fa99f2a91dcb3170", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "2a6b84f218d7695b8019641a209484c2822a1c294fc2b0bdfebfaa86493b9de7", "generation_seconds_batch": 22.906167623004876, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5962055921554565, "target_z": 1.2890625933839222, "ce": 6.459460258483887, "genuineness": 4.174716949462891, "identity": 0.35062146186828613, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/52054f5e8a5b7d6b8b702790e1fae6b565970196c7c6e452fa99f2a91dcb3170.mp3" }, { "id": "emo_Amusement-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-0", "key": "521d2bb2b2450bacd32fd4a41296e31a26e443d239a87cb22aadb24395761dd8", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "b39e2110036097da860d4f27b48a9d9d16fe45a7c83780d1890d9552ad734a7f", "generation_seconds_batch": 23.062264002044685, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.474191427230835, "target_z": 1.1484374495512144, "ce": 6.340320587158203, "genuineness": 4.042920112609863, "identity": 0.46623867750167847, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/521d2bb2b2450bacd32fd4a41296e31a26e443d239a87cb22aadb24395761dd8.mp3" }, { "id": "emo_Amusement-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-0", "key": "52a8eb08d335c7c9abc1c6a55428ebdba3a12477836d0b8aa04cf8e4b86b1333", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The door is still open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "8ef0f9b64e766848fa62f3472ab874b34652c3fd5475d98ddbf6b076e25ae260", "generation_seconds_batch": 22.576626166002825, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0403637886047363, "target_z": 0.648437518247433, "ce": 6.141753673553467, "genuineness": 3.886019229888916, "identity": 0.5636380910873413, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/52a8eb08d335c7c9abc1c6a55428ebdba3a12477836d0b8aa04cf8e4b86b1333.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": "53141297bc0c6fae0c922868b94912997f76ab2db5493a813b52191951ea80b1", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f3fb5e7e1da6abf46c96d97be773d0b7df2fc5ca1f32f12e1f3b9150d98ab3ca", "generation_seconds_batch": 16.80185003299266, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.484196424484253, "target_z": 2.3124998196724262, "ce": 6.197352409362793, "genuineness": 4.507347106933594, "identity": 0.6020222902297974, "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_Amusement/53141297bc0c6fae0c922868b94912997f76ab2db5493a813b52191951ea80b1.mp3" }, { "id": "emo_Amusement-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-1", "key": "535cb31aba4ad95d4054c3d316d5174a9d9f8bb6d48c2906467aaa71e8b7ec72", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "ffcb455d2347e6788bdb8442954779b787417afd9a27800516a5ad5a9b6d567e", "generation_seconds_batch": 23.422579201986082, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6468818187713623, "target_z": 2.4999998282594533, "ce": 6.0146708488464355, "genuineness": 4.024092197418213, "identity": 0.7182539701461792, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/535cb31aba4ad95d4054c3d316d5174a9d9f8bb6d48c2906467aaa71e8b7ec72.mp3" }, { "id": "emo_Amusement-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-0", "key": "53cfa7c185535a121bfbfa6e5ae483b9ad52f8ffaa12099403a6825476582270", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De deur staat nog open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "66be858f6faafd2018740294f2a0a5213edaa580f945c91debb900216fe92d86", "generation_seconds_batch": 23.873053429997526, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.619767665863037, "target_z": 2.4687499184232404, "ce": 6.165581703186035, "genuineness": 4.268857479095459, "identity": 0.3087291717529297, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/53cfa7c185535a121bfbfa6e5ae483b9ad52f8ffaa12099403a6825476582270.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": "541bd8923759091daf8bb049a53d1ca1928ea7db9c26456f74d6faeeefd6cb1f", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "3eea1b10d5e408a68d4b591834a7b67b0232ff9606e3380c3756f09e10ddc04d", "generation_seconds_batch": 17.211506263003685, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0129239559173584, "target_z": 2.921874847580265, "ce": 6.1020402908325195, "genuineness": 4.281409740447998, "identity": 0.5717853307723999, "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_Amusement/541bd8923759091daf8bb049a53d1ca1928ea7db9c26456f74d6faeeefd6cb1f.mp3" }, { "id": "emo_Amusement-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-1", "key": "5434d37e6ee7e397aa6a0f3a3e14a780c6778e87827b1a7c43bb58885cece6cd", "bucket": "emo_Amusement", "phase": "wording", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I found the little box.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It was beside the old window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "53fcc5fb2c3439dc7b8c8c5ef07bcf39699e12635102fca5d1e6f1dc0ea41107", "generation_seconds_batch": 18.075810362934135, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1520471572875977, "target_z": 1.9296873937355368, "ce": 6.292664527893066, "genuineness": 4.306513786315918, "identity": 0.3059243857860565, "hypothesis": "I found the little box. It was beside the old window. We can look inside together,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/5434d37e6ee7e397aa6a0f3a3e14a780c6778e87827b1a7c43bb58885cece6cd.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_Amusement", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": "00b64cbd932cea14fe414413fb118135492bd9d133dfb13c27c149bdea95c246", "generation_seconds_batch": 17.006485942052677, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.31929469108581543, "target_z": -0.18261718441403704, "ce": 6.23706579208374, "genuineness": 4.21237325668335, "identity": 0.5079696774482727, "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_Amusement/546203f143d2dbd908be3097fd76d41d76e93afd1487fa15c64a3d119dff5d49.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": "554e242d90e1a51390dd863d9b5f8b89964a77fa067b53d393891cfc22f8fdd7", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The road turns left behind the bridge.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6d583dae42f475278cca309c9d4bbb72ed0a4fcf79f6381775934ecf3d357c2b", "generation_seconds_batch": 20.36777614802122, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8590373396873474, "target_z": 0.439453110777736, "ce": 6.38797664642334, "genuineness": 3.9676074981689453, "identity": 0.3716139495372772, "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_Amusement/554e242d90e1a51390dd863d9b5f8b89964a77fa067b53d393891cfc22f8fdd7.mp3" }, { "id": "emo_Amusement-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-1", "key": "557b6f07b46c6cd9ae736ead7deefa99fd94759df849d1ee9fa9e87dcff4c848", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "bd400cd8e47c3c140431097f24ae8fb9bb22886af1b25c814e1c89fb7cfa8b43", "generation_seconds_batch": 23.107993464916945, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2298378944396973, "target_z": 3.1718749506245927, "ce": 5.824047088623047, "genuineness": 4.030367851257324, "identity": -0.07105666399002075, "hypothesis": "Ik heb het kleine doosje gevonden en stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/557b6f07b46c6cd9ae736ead7deefa99fd94759df849d1ee9fa9e87dcff4c848.mp3" }, { "id": "emo_Amusement-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-0", "key": "55b42a1346cc7bbf4c1bbae839e6941530845c446b5db2c879484d6e1aa30369", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "7928eca1715afc56ea47c2342557f5b0c522fc791c8e2081bbf454df2412a6df", "generation_seconds_batch": 23.617233429918997, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6468818187713623, "target_z": 2.4999998282594533, "ce": 5.80021858215332, "genuineness": 3.5847692489624023, "identity": 0.4466938376426697, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/55b42a1346cc7bbf4c1bbae839e6941530845c446b5db2c879484d6e1aa30369.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": "55d60a778669a4283e463a7891383e520864bb20e8c446384aaec05afa94a396", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "15d749559e2f5b18845e3cf3a44ac6f92aef12f9866ad48f23403dc28bf11fdb", "generation_seconds_batch": 20.099594148923643, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6300983428955078, "target_z": 1.328125049375407, "ce": 6.268836498260498, "genuineness": 4.3881025314331055, "identity": 0.5655384659767151, "hypothesis": "J'ai écrit le numéro sur l'enveloppe. Lis-le bien et vérifie les deux derniers chiffres. Appelle-moi quand s'il y aura un moment.", "wer": 0.13636363636363635, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/55d60a778669a4283e463a7891383e520864bb20e8c446384aaec05afa94a396.mp3" }, { "id": "emo_Amusement-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-1", "key": "5650e40843a500c79a76c18d66a337291687669728b3484b39d6391ffcdda98a", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I found the little box.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It was beside the old window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "a890711e4c7e9c1e4e7bf28b1cacb3db8217d4915fe4182a0aca671604687d25", "generation_seconds_batch": 25.157122698961757, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.901240587234497, "target_z": 1.6406249720921613, "ce": 6.284721851348877, "genuineness": 4.394378662109375, "identity": 0.5283929705619812, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/5650e40843a500c79a76c18d66a337291687669728b3484b39d6391ffcdda98a.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": "56e9472b0449685fb06455b464ca2d3bd995659a2864bb74647afe391c53cec3", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I wrote the number on the envelope.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "620a346367670392967adec1d0ddd923de93239d1e4b0bc4078ec616c29361d4", "generation_seconds_batch": 20.176264434005134, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4064059257507324, "target_z": 1.0703125375682445, "ce": 6.229123115539551, "genuineness": 4.243753433227539, "identity": 0.4792180061340332, "hypothesis": "I wrote the number on the envelope, write it carefully, and check the last two digits. Call me when you have a moment.", "wer": 0.043478260869565216, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/56e9472b0449685fb06455b464ca2d3bd995659a2864bb74647afe391c53cec3.mp3" }, { "id": "emo_Amusement-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-1", "key": "570e362c9ded94ff1ee973290af5a6208bec8c46954fa2a67c3ba087b4c7a838", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I found the little box.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It was beside the old window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "0c02ed3b8663fb9ea4d3282b35a422872866dde4ce5e84e2e4a7f0e87d701597", "generation_seconds_batch": 18.885680835926905, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1620521545410156, "target_z": 3.0937497638567484, "ce": 5.95112943649292, "genuineness": 4.243753433227539, "identity": 0.5581555366516113, "hypothesis": "I found the little box It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/570e362c9ded94ff1ee973290af5a6208bec8c46954fa2a67c3ba087b4c7a838.mp3" }, { "id": "emo_Amusement-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-1", "key": "578ccf02eced85fcd84f98bafdbffb14d1da5a6a2ec11a3b8851c0cba6c8ddb7", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "9b6e0274666fd9011f99969fd46a23c96024b43b73c70a9c9d7b38f309858dda", "generation_seconds_batch": 17.696634375024587, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0639259815216064, "target_z": 1.8281249806791886, "ce": 5.998785495758057, "genuineness": 4.18099308013916, "identity": 0.5694047212600708, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/578ccf02eced85fcd84f98bafdbffb14d1da5a6a2ec11a3b8851c0cba6c8ddb7.mp3" }, { "id": "emo_Amusement-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-0", "key": "593c998f96cd662a90d77a83e27f2c8a064ba131568ec517bd3e23b8e67032df", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "d378446725f03ad2f8a90fa6d366fae68cf864f603b14649d473aa8624bebedd", "generation_seconds_batch": 22.412649714038707, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8403962850570679, "target_z": 0.41796871189506624, "ce": 6.316492557525635, "genuineness": 4.331617832183838, "identity": 0.3986882269382477, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/593c998f96cd662a90d77a83e27f2c8a064ba131568ec517bd3e23b8e67032df.mp3" }, { "id": "emo_Amusement-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-0", "key": "59e15c7496f91e67acc3f9a4043388d677f0b0d9d8b0af5f8d1ea092d1b24f9a", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "21f41e50f5f0a723f816904e2b14dfb9555422b9d949111d07f2b20a2b199c28", "generation_seconds_batch": 22.025553654995747, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2403311729431152, "target_z": 0.8789061872073627, "ce": 6.252951145172119, "genuineness": 4.394378662109375, "identity": 0.7549526691436768, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/59e15c7496f91e67acc3f9a4043388d677f0b0d9d8b0af5f8d1ea092d1b24f9a.mp3" }, { "id": "emo_Amusement-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-0", "key": "59e4b5b4c4eaed5315b3bd6105bfe12225d9fc6c5f897773636e3595e39d43bb", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "390ef330b22357e191da27742463e01768110eebded29a220f1766b82b4aed32", "generation_seconds_batch": 16.972640816005878, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.375739574432373, "target_z": 2.1874999055426994, "ce": 6.308549880981445, "genuineness": 4.425758361816406, "identity": 0.6152317523956299, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/59e4b5b4c4eaed5315b3bd6105bfe12225d9fc6c5f897773636e3595e39d43bb.mp3" }, { "id": "emo_Amusement-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-1", "key": "5b413fd0cd5e03cd1e86ff26ecbe44fcf6675ca8d7e90680c65200c6ed1a0312", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5eedd0153d4d9ad9c16e26f3c27720f8c81ddecfbef148b067831b902b2c9dc3", "generation_seconds_batch": 24.14048035198357, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.619767665863037, "target_z": 2.4687499184232404, "ce": 5.911416053771973, "genuineness": 3.528284788131714, "identity": 0.24498286843299866, "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_Amusement/5b413fd0cd5e03cd1e86ff26ecbe44fcf6675ca8d7e90680c65200c6ed1a0312.mp3" }, { "id": "emo_Amusement-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-1", "key": "5b702b032a18c559a92254ca007f30b19c0a793e49492700c9b15a2471d80247", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I found the little box.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It was beside the old window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "f8d0a791ae827071242004b9296608b64c1508978b63cffec508e5f4c5958c00", "generation_seconds_batch": 17.316926753963344, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5519821643829346, "target_z": 2.3906250064402705, "ce": 6.24500846862793, "genuineness": 3.9927117824554443, "identity": 0.40354660153388977, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/5b702b032a18c559a92254ca007f30b19c0a793e49492700c9b15a2471d80247.mp3" }, { "id": "emo_Amusement-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-0", "key": "5bd2f969403cbf5f9fca7c6176bec5ebc9b75fcfe85c2fd5a819c4382ada9b1c", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "393c82d7c2e4859e7a8fc3dfeeb69f5475684322504eb8ba3a1631415a61cb18", "generation_seconds_batch": 18.502018918981776, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3079540729522705, "target_z": 2.1093749935597295, "ce": 6.300607204437256, "genuineness": 4.287685871124268, "identity": 0.49296557903289795, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/5bd2f969403cbf5f9fca7c6176bec5ebc9b75fcfe85c2fd5a819c4382ada9b1c.mp3" }, { "id": "emo_Amusement-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-0", "key": "5c0d4f10145504fec7e875d855cc47aae577d95644b7bde89df17aa23a81127b", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The door is still open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "4917be10e7df839002ad0b28ec6c768fcb3ac4906828b288b0de706ceb11b10b", "generation_seconds_batch": 24.782631139969453, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.240168571472168, "target_z": 2.0312500815767596, "ce": 6.221180438995361, "genuineness": 3.8671910762786865, "identity": 0.49338090419769287, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/5c0d4f10145504fec7e875d855cc47aae577d95644b7bde89df17aa23a81127b.mp3" }, { "id": "emo_Amusement-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-1", "key": "5caa39fc57b9a1848d7f8c12051575bdec6a2a4fa3d2471082233aaaa59d11db", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I found the little box.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It was beside the old window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "11b2ae5908fa4ddcbc60a78e0fb0cbac2641d97f50150ff00f0e79434d3ecf54", "generation_seconds_batch": 26.469425132032484, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.962247610092163, "target_z": 1.7109374753122963, "ce": 6.332377910614014, "genuineness": 4.193545341491699, "identity": 0.4197758734226227, "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_Amusement/5caa39fc57b9a1848d7f8c12051575bdec6a2a4fa3d2471082233aaaa59d11db.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": "5ccaf12cea4ebd0e49da14aae1304d674854230b3c793d748956413e5ad59f66", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Your message arrived after I had left.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8d3f670ec4a67a8c55c88af1f77ebda28238521327e53bc5341df37c9bbd1a50", "generation_seconds_batch": 15.504822029964998, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8809049129486084, "target_z": 1.6171874710187828, "ce": 6.38797664642334, "genuineness": 4.293961524963379, "identity": 0.2505083382129669, "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_Amusement/5ccaf12cea4ebd0e49da14aae1304d674854230b3c793d748956413e5ad59f66.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": "5cfc529d949d26ce3dba38105e03e51dc4cf1c2091818e95218ff1cb63181173", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6159ca693d0800d12972b3d0238b21da19639f52bcecb6d8eefae7ea2e0bac9b", "generation_seconds_batch": 19.573803259059787, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.084261655807495, "target_z": 1.8515624817525669, "ce": 6.324435234069824, "genuineness": 4.293961524963379, "identity": 0.35912182927131653, "hypothesis": "Die Schlüsse liegen auf dem Küchentisch. Ich suchte in der Schublade, dann neben dem Fenster. Nimm sie mit, wenn du gehst.", "wer": 0.047619047619047616, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/5cfc529d949d26ce3dba38105e03e51dc4cf1c2091818e95218ff1cb63181173.mp3" }, { "id": "emo_Amusement-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-0", "key": "5d1193e1873e0961768b5c370fe3949503baf356275999969eca6851af988bd1", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "33def3853621afd407b6b3f2cb43b38096117476c9c88a3ee25cd3347bae7e16", "generation_seconds_batch": 24.35164685593918, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.850238561630249, "target_z": 2.734374838993238, "ce": 6.086154937744141, "genuineness": 4.118232727050781, "identity": 0.5979079008102417, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/5d1193e1873e0961768b5c370fe3949503baf356275999969eca6851af988bd1.mp3" }, { "id": "emo_Amusement-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-1", "key": "5d8a8403e04ccfc4cfe5a9fb344b49e19b35fbc1f93a7fd71cf180527602744b", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "5a0218c599dbc954aa0990f368b38997bab8f9a833df3f77e1413b0bb1bb38e6", "generation_seconds_batch": 21.70721016090829, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8319231271743774, "target_z": 0.4082031322453043, "ce": 6.173524379730225, "genuineness": 4.293961524963379, "identity": 0.6295055747032166, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/5d8a8403e04ccfc4cfe5a9fb344b49e19b35fbc1f93a7fd71cf180527602744b.mp3" }, { "id": "emo_Amusement-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-1", "key": "5dec704fe2ed1e0049df33f189350a5b7a673d65d5b0f78e863ba251dbdc1d87", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "ce9cc0c2db2841e5006f4d87b780062d07b90a742d9974776f09348c054bb6c4", "generation_seconds_batch": 18.119773142039776, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8773529529571533, "target_z": 2.765625023614325, "ce": 6.229123115539551, "genuineness": 4.400654315948486, "identity": 0.6597291231155396, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/5dec704fe2ed1e0049df33f189350a5b7a673d65d5b0f78e863ba251dbdc1d87.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_Amusement", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": "b6aff86eda4bc15d4e39d4f0e28fc23218e66d7f37a5a2aa51ea68a9c61f3182", "generation_seconds_batch": 17.693145637982525, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24896715581417084, "target_z": -0.2636718699014525, "ce": 6.022613525390625, "genuineness": 4.168440818786621, "identity": 0.7551060914993286, "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_Amusement/5e0af124ad7421917e897f2876d49b25e213a1bc87e01fe43f09b9c255c2a32f.mp3" }, { "id": "emo_Amusement-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-0", "key": "5ea1a529abf529b337aac73ef4af4910de25b2c79bd75c277281775c1f95fe4f", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "8496230c277f356abc166aefe2096f0da77f6155299badd10a1e9da3efe4f5b1", "generation_seconds_batch": 18.306890400941484, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1113758087158203, "target_z": 1.88281239158878, "ce": 5.839932441711426, "genuineness": 4.18099308013916, "identity": 0.5594756007194519, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/5ea1a529abf529b337aac73ef4af4910de25b2c79bd75c277281775c1f95fe4f.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": "5ea8c0ffff2b929b5f863266eeda251b35296df0df863d3300d848f9fae423a5", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2c7238cc3b0a53bbf856d2a8b7ea48b98a56a4a1603636b8376de4defc688232", "generation_seconds_batch": 15.110584764974192, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7317767143249512, "target_z": 1.4453125547422991, "ce": 6.38797664642334, "genuineness": 4.344170093536377, "identity": 0.6511639356613159, "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_Amusement/5ea8c0ffff2b929b5f863266eeda251b35296df0df863d3300d848f9fae423a5.mp3" }, { "id": "emo_Amusement-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-1", "key": "5f3ed83572c8524dd74d1b01f821908319486af1d14945b1999e41c7998d772f", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I found the little box.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It was beside the old window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "ff122070ef94556603ffa82ea4ea04efd85c32a26ae7079d6aa8d9d836b72b1f", "generation_seconds_batch": 26.469425132032484, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1859400272369385, "target_z": 1.968749987119459, "ce": 6.348263263702393, "genuineness": 4.369274139404297, "identity": 0.31490761041641235, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/5f3ed83572c8524dd74d1b01f821908319486af1d14945b1999e41c7998d772f.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": "5f56ed88e0d277dd8aa121b6e27cb74a86b48ea1cef46c56f8ff2701159c5671", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "53e5f9cb114b15151278b1d6fb8169cbe136ce5d88d7d3e22e86f030437d62aa", "generation_seconds_batch": 20.252199482056312, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2843918800354004, "target_z": 0.9296875311279741, "ce": 6.324435234069824, "genuineness": 3.9299514293670654, "identity": 0.537317156791687, "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_Amusement/5f56ed88e0d277dd8aa121b6e27cb74a86b48ea1cef46c56f8ff2701159c5671.mp3" }, { "id": "emo_Amusement-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-1", "key": "5f7313c50cdea69e8f71fa26b4b784733f6f8051822f5c35db185b3f85545736", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "90a1e272d256d54e52d85ac0f7784f6ba19d1a7e39b65b59795d4fc559ec0570", "generation_seconds_batch": 21.06697072996758, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.267282724380493, "target_z": 2.0624999914129725, "ce": 6.173524379730225, "genuineness": 4.2374773025512695, "identity": 0.5905859470367432, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/5f7313c50cdea69e8f71fa26b4b784733f6f8051822f5c35db185b3f85545736.mp3" }, { "id": "emo_Amusement-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-0", "key": "5f9fc33f0fd0fa7e6c7a33d9eda6221de396ab60f37d91490d9f5a1e6c7e7658", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De deur staat nog open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "eee9bbaf8fb1f097a5f56b4101c591e4906ffb49638a184dede27e0628356e65", "generation_seconds_batch": 24.094824225991033, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6233197450637817, "target_z": 1.3203125032201353, "ce": 6.117925643920898, "genuineness": 4.193545341491699, "identity": 0.5495502948760986, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/5f9fc33f0fd0fa7e6c7a33d9eda6221de396ab60f37d91490d9f5a1e6c7e7658.mp3" }, { "id": "emo_Amusement-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-1", "key": "6041c66886e772f6b8fbffc188b597793c436fed4d689e4f128c8cbe289576fb", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "81835b92a90bf18b7fef8be714d35da84f61bd88df1a08b2966afaaddf62ddd9", "generation_seconds_batch": 22.481750952079892, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2267740964889526, "target_z": 0.8632812322892561, "ce": 6.41180419921875, "genuineness": 4.055472373962402, "identity": 0.4914170503616333, "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_Amusement/6041c66886e772f6b8fbffc188b597793c436fed4d689e4f128c8cbe289576fb.mp3" }, { "id": "emo_Amusement-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-1", "key": "60a65b2b0332071e7e52ab600b8ff769884bbb033b2caaf5c688bfb564cde7f3", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "9301e72f04a95a5a43459fd798a7ee6ac1ff30dcacaab29d659f197678f2a4e9", "generation_seconds_batch": 21.925576448091306, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8266764879226685, "target_z": 1.5546875139539194, "ce": 5.6532793045043945, "genuineness": 4.042920112609863, "identity": 0.49351412057876587, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/60a65b2b0332071e7e52ab600b8ff769884bbb033b2caaf5c688bfb564cde7f3.mp3" }, { "id": "emo_Amusement-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-0", "key": "60c206f7b3837058b6d0d7c7adf7a4efd497a6f19cff2d181311553531582b09", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "37fdf961fbece20839eac677d3f04a64f4a99db98f2d733680e5380f610ee1f6", "generation_seconds_batch": 26.3998201219365, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1078238487243652, "target_z": 3.0312499441843226, "ce": 5.871703147888184, "genuineness": 3.722842216491699, "identity": 0.4996105432510376, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/60c206f7b3837058b6d0d7c7adf7a4efd497a6f19cff2d181311553531582b09.mp3" }, { "id": "emo_Amusement-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-0", "key": "60d8870dccfa8e9a29fa7603919e1b8e93bafc99219a51a2315137e2bd800d69", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "de5bbd5faa40f335614a8a1b77ceed4e4bb08c6944e8a48848ec03607b8bde2a", "generation_seconds_batch": 24.61685392598156, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8437855839729309, "target_z": 0.4218749849727022, "ce": 6.1894097328186035, "genuineness": 4.331617832183838, "identity": 0.6457274556159973, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/60d8870dccfa8e9a29fa7603919e1b8e93bafc99219a51a2315137e2bd800d69.mp3" }, { "id": "emo_Amusement-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-1", "key": "61461100e000a60681b6f5054c580fd7b753eaa8cfb650604669bda383f4bfb1", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "776c159184641adef6ad8a5e6762793d97621ecb4262a30b5bfb789016d7b255", "generation_seconds_batch": 23.427003188058734, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8470121622085571, "target_z": 1.5781250150272979, "ce": 6.475345611572266, "genuineness": 4.356721878051758, "identity": 0.48666810989379883, "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_Amusement/61461100e000a60681b6f5054c580fd7b753eaa8cfb650604669bda383f4bfb1.mp3" }, { "id": "emo_Amusement-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-1", "key": "61eacd21a3101cc9e4a506a1f981b6fe40c03b8cec9313af0058ef499e0c872e", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "2567b5d0d6e98d493a82d9b70ca70fa91ab3da74ebd115ab5c7c102239be75d4", "generation_seconds_batch": 17.245006195036694, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.243720531463623, "target_z": 0.8828125289812172, "ce": 6.292664527893066, "genuineness": 4.582659721374512, "identity": 0.6446373462677002, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/61eacd21a3101cc9e4a506a1f981b6fe40c03b8cec9313af0058ef499e0c872e.mp3" }, { "id": "emo_Amusement-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-1", "key": "621550ca0e1034a9404954a41716c617e2690aeff9e864bcc0aab82bbbbfa1cc", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "b96bee4aa3acb9dae740f3833224833eaeaf449e6174784eea415a8b0ae53ccc", "generation_seconds_batch": 23.81260333303362, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9554691314697266, "target_z": 1.7031250665494617, "ce": 6.1020402908325195, "genuineness": 4.137060642242432, "identity": 0.38417527079582214, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/621550ca0e1034a9404954a41716c617e2690aeff9e864bcc0aab82bbbbfa1cc.mp3" }, { "id": "emo_Amusement-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-0", "key": "629fa00421b730ee9bbde2b4d61ddcc35cca8431c35ed136e867c2236de321f5", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c7aab6ffed5363bbe492e8bc614c17ad21ca8f1b15f0d07b01c81a68411c4e99", "generation_seconds_batch": 24.05707928701304, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4435253143310547, "target_z": 2.2656250923105437, "ce": 6.006728172302246, "genuineness": 4.3881025314331055, "identity": 0.5601562857627869, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/629fa00421b730ee9bbde2b4d61ddcc35cca8431c35ed136e867c2236de321f5.mp3" }, { "id": "emo_Amusement-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-1", "key": "62bbe8eccd51991fe546e4e795032173075953125f522251785bba63272ea5c2", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "00beac6eb2c6dfc1c9f9224eefcbad8250942bd7f381d121e5c01ba0f9fb291b", "generation_seconds_batch": 24.48272975999862, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3996273279190063, "target_z": 1.0624999914129727, "ce": 6.125868320465088, "genuineness": 4.3881025314331055, "identity": 0.4404960870742798, "hypothesis": "J'ai trouvé la 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_Amusement/62bbe8eccd51991fe546e4e795032173075953125f522251785bba63272ea5c2.mp3" }, { "id": "emo_Amusement-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-1", "key": "63b3e285ae83f3cc7367792493d826de97183c32cf7c8d68b07fc20c39be56c8", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "1b384108f7ea90ca6c1da8c43b7eb24365bb1de01d4cf42a99798e1ff05e9007", "generation_seconds_batch": 24.997748160967603, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8334550857543945, "target_z": 1.5625000601091912, "ce": 6.260893821716309, "genuineness": 4.532451152801514, "identity": 0.5303817391395569, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/63b3e285ae83f3cc7367792493d826de97183c32cf7c8d68b07fc20c39be56c8.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": "63cdb55dd75bfc06f61567c9cc1ff674d74de9000d44752b3ac64bc8c841ec38", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5d71ecdade8eeb53d6a42fa64f61c3f041ded5a7a37f8bac1928d84e8dafdead", "generation_seconds_batch": 17.976285106036812, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5790963172912598, "target_z": 2.4218749162764834, "ce": 6.149696350097656, "genuineness": 4.356721878051758, "identity": 0.14673911035060883, "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_Amusement/63cdb55dd75bfc06f61567c9cc1ff674d74de9000d44752b3ac64bc8c841ec38.mp3" }, { "id": "emo_Amusement-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-0", "key": "640562026391c2a18f57d9498ebb0f35a8a0f1992b5fd8c91f28a1236fe3a265", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "a99ddbc1e66a957ba4ecbb3501a6f862f4ee9248bbe7921ac579c520e8a5e62b", "generation_seconds_batch": 23.632585786050186, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7927837371826172, "target_z": 1.5156250579624344, "ce": 5.550024509429932, "genuineness": 3.2584152221679688, "identity": 0.31960731744766235, "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_Amusement/640562026391c2a18f57d9498ebb0f35a8a0f1992b5fd8c91f28a1236fe3a265.mp3" }, { "id": "emo_Amusement-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-1", "key": "641f339dc67c7d741bc7bba062ed3882c499e203936014a61138fa8f7d5d0a1e", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "a2087a52170cc1eb2819c6e64fcf23a94f90dd48e5a897effdb2a1f8c26bee81", "generation_seconds_batch": 22.380848158034496, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7114410400390625, "target_z": 1.4218750536689209, "ce": 6.332377910614014, "genuineness": 4.268857479095459, "identity": 0.6409712433815002, "hypothesis": "J'ai trouvé la 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_Amusement/641f339dc67c7d741bc7bba062ed3882c499e203936014a61138fa8f7d5d0a1e.mp3" }, { "id": "emo_Amusement-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-1", "key": "64282e9e38de84d61d7caeb11a158cc6d62fa8b800a1d18a8a82f546756036fc", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3d1d7fc09c2bc7b49f82592d408632c51170bedc13be67bcdd7f93f95ad38493", "generation_seconds_batch": 23.190377993974835, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1113758087158203, "target_z": 1.88281239158878, "ce": 6.316492557525635, "genuineness": 3.7918784618377686, "identity": 0.35488975048065186, "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_Amusement/64282e9e38de84d61d7caeb11a158cc6d62fa8b800a1d18a8a82f546756036fc.mp3" }, { "id": "emo_Amusement-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-1", "key": "642b5a64dc84f84ef94caaf5a667df8edaf1f701843f3fe2b5ff4f3b51d288ff", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f9db8b4782e550222c1d72ef5e9af8f8078754525dcbd601235741406b6e7fac", "generation_seconds_batch": 22.335996659006923, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8266764879226685, "target_z": 1.5546875139539194, "ce": 6.133810997009277, "genuineness": 4.413206577301025, "identity": 0.6527835726737976, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/642b5a64dc84f84ef94caaf5a667df8edaf1f701843f3fe2b5ff4f3b51d288ff.mp3" }, { "id": "emo_Amusement-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-1", "key": "64562a4ad185e92d7f47991cc4fa118787d0863842ade082f72da295ffe44fcd", "bucket": "emo_Amusement", "phase": "wording", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "4483ba29ec01bd1cb7607e0aa5f3425ea45599eff11001f6d27990cb428280f3", "generation_seconds_batch": 17.74995131394826, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8673478364944458, "target_z": 1.6015625161006761, "ce": 6.1020402908325195, "genuineness": 4.406930446624756, "identity": 0.6254334449768066, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/64562a4ad185e92d7f47991cc4fa118787d0863842ade082f72da295ffe44fcd.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": "64dd2fd8b9394934e10fd519d5c6cdcb1edadacf32cf4f38bfae108d11906ccb", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9bd3a118b8de70fda58517a39dd18796681dfddf31ce73ab27db85cdb2c7fbb0", "generation_seconds_batch": 17.499346739961766, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2098276615142822, "target_z": 0.843749935597295, "ce": 6.197352409362793, "genuineness": 4.319066047668457, "identity": 0.807363748550415, "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_Amusement/64dd2fd8b9394934e10fd519d5c6cdcb1edadacf32cf4f38bfae108d11906ccb.mp3" }, { "id": "emo_Amusement-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-0", "key": "652b5d61f7ddae51b298710e39275d37299b4728ea37b82ba5a2a7b5d1a78d94", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "210a2bbc8aa350c13f0964ab4a3e6402e4dea119243ea9d5c80dac794c7acde2", "generation_seconds_batch": 23.329139773966745, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0435903072357178, "target_z": 1.80468747960581, "ce": 6.157639026641846, "genuineness": 4.086852550506592, "identity": 0.2285163402557373, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/652b5d61f7ddae51b298710e39275d37299b4728ea37b82ba5a2a7b5d1a78d94.mp3" }, { "id": "emo_Amusement-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-0", "key": "65b746c78ba785277afe5f36327f31648598b9db484a61c28dc6c8653d6b4826", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "1a2f6b4a9f22117bcb2e810aa69737d26234c6160c3d964c421e08714e9ed98f", "generation_seconds_batch": 25.114338336046785, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.206275701522827, "target_z": 1.9921874881928374, "ce": 5.974957466125488, "genuineness": 4.13078498840332, "identity": 0.48736661672592163, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/65b746c78ba785277afe5f36327f31648598b9db484a61c28dc6c8653d6b4826.mp3" }, { "id": "emo_Amusement-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-0", "key": "66261e642a34d710c5bb7df1c74aaf1913144255acec7483d19feb121dd03551", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "93f98c5f732939d487e25b57adb07341dc71fe1bdb886d753f4831730b0477af", "generation_seconds_batch": 16.713281935080886, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.009697437286377, "target_z": 1.765624886221888, "ce": 5.974957466125488, "genuineness": 3.860914945602417, "identity": 0.6018415689468384, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/66261e642a34d710c5bb7df1c74aaf1913144255acec7483d19feb121dd03551.mp3" }, { "id": "emo_Amusement-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-1", "key": "66589a7a1f1d2b066a4bbddbea93e59ce372e5afe85708bf6f4b583c9c01a278", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2a3c8f07a32a1319233a91082228a610b05deb5321d174d60d3eb8ab06833b15", "generation_seconds_batch": 21.367572588962503, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2808399200439453, "target_z": 2.0781250837235166, "ce": 6.523001670837402, "genuineness": 4.068024158477783, "identity": 0.39473867416381836, "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_Amusement/66589a7a1f1d2b066a4bbddbea93e59ce372e5afe85708bf6f4b583c9c01a278.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": "66e59b1bbc46425b3a529779495b1200dcb60c264625413b0e8ef65861e22037", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d6646e5d5328ee2dc95cd8c6e0b90810b5e93cb510d0c2d8292acb5602c8db3e", "generation_seconds_batch": 17.04972067498602, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5623127222061157, "target_z": 1.25, "ce": 6.395919322967529, "genuineness": 4.256305694580078, "identity": 0.4480780363082886, "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_Amusement/66e59b1bbc46425b3a529779495b1200dcb60c264625413b0e8ef65861e22037.mp3" }, { "id": "emo_Amusement-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-1", "key": "66fd18be1b8f0f58ca46d86126e7c637313b4ea6204277d1a71024ab6a0e4f48", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "f85eb64549001bc672f46e8b5d1094626e273c8ce189b9e0b018008e097c3e29", "generation_seconds_batch": 18.20235988101922, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7960102558135986, "target_z": 2.6718750193208116, "ce": 6.205295085906982, "genuineness": 4.268857479095459, "identity": 0.5254600048065186, "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_Amusement/66fd18be1b8f0f58ca46d86126e7c637313b4ea6204277d1a71024ab6a0e4f48.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": "67f1ac8cfbdfc55e7c4c3744fd31b2d1f0d70044c6468d02a1b84c70261b00fa", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [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": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "a23334a7abb3e120dddab40cb0f772c2378446cd71fe0a6786b7dd625fab9fc4", "generation_seconds_batch": 16.778751206002198, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5980628728866577, "target_z": 0.13867186990145253, "ce": 6.133810997009277, "genuineness": 4.093128204345703, "identity": 0.5135202407836914, "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_Amusement/67f1ac8cfbdfc55e7c4c3744fd31b2d1f0d70044c6468d02a1b84c70261b00fa.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": "68742ff309f845d6e8461755ab16fb755ff8db5dbce535b71258e977962bd75c", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The keys are on the kitchen table.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1efcd1d34d852b69e045088823ede411ac9b119eef3989c9951b716d7ae6264b", "generation_seconds_batch": 22.57794579898473, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9690262079238892, "target_z": 1.7187500214675684, "ce": 6.419747352600098, "genuineness": 3.9299514293670654, "identity": 0.34948307275772095, "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_Amusement/68742ff309f845d6e8461755ab16fb755ff8db5dbce535b71258e977962bd75c.mp3" }, { "id": "emo_Amusement-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-0", "key": "6a22cedc14e7b7629c293e7d7c0f95d72bea517d22bca40402f548fdc0a3709b", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1247373455bee4b934511bcaf7f25bdf506addc3c4d22d273b7fa0dd77e3c583", "generation_seconds_batch": 16.689911424997263, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6604390144348145, "target_z": 2.5156249205699974, "ce": 6.221180438995361, "genuineness": 4.331617832183838, "identity": 0.4937444031238556, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/6a22cedc14e7b7629c293e7d7c0f95d72bea517d22bca40402f548fdc0a3709b.mp3" }, { "id": "emo_Amusement-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-1", "key": "6a295c8eeaafeabf791a50d3de3a9a5608751013ac1309e3395b3e00c51982c3", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "c6af3cb1395adc20fb7b5d9925bb3b0702040c189ef871d2f89fb0ba4e3541fb", "generation_seconds_batch": 22.59440247400198, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3621826171875, "target_z": 2.17187508801703, "ce": 6.149696350097656, "genuineness": 4.086852550506592, "identity": 0.40242430567741394, "hypothesis": "J'ai trouvé la 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_Amusement/6a295c8eeaafeabf791a50d3de3a9a5608751013ac1309e3395b3e00c51982c3.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_Amusement", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": "2d835c1c3c3d40ab9ff62a3c75ab6573a2caaf9261f46bea539d8d77e592dcf4", "generation_seconds_batch": 17.667185041005723, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6141619682312012, "target_z": 0.15722658114994997, "ce": 6.332377910614014, "genuineness": 4.042920112609863, "identity": 0.14225926995277405, "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_Amusement/6a61bc20d43b3e97640d8dd45682f7055c5dbaa5aa987cdb55f8a7d7a432a2c2.mp3" }, { "id": "emo_Amusement-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-0", "key": "6b1b4859882ce2d3479a0e4118b433a29274f496edf80c62de31c6f3601e33eb", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The door is still open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "b1ded4e04711ba8835e7075357720f2ac86f2234baddb659bb8935bef29024ed", "generation_seconds_batch": 23.616935844998807, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6333248615264893, "target_z": 2.484375010733784, "ce": 6.0305562019348145, "genuineness": 3.3337275981903076, "identity": 0.5121681094169617, "hypothesis": "The 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_Amusement/6b1b4859882ce2d3479a0e4118b433a29274f496edf80c62de31c6f3601e33eb.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": "6b1f4a4faf32429c22ecafaf888f8531f8be18600b4a31b8302a4fb47eac8b8c", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a816ba8345975d93e176dc112ec0915ad2bbc3950f50dd5b262eee9f9313cfdf", "generation_seconds_batch": 16.71423181402497, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8470121622085571, "target_z": 1.5781250150272979, "ce": 6.268836498260498, "genuineness": 4.457139015197754, "identity": 0.3056621551513672, "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_Amusement/6b1f4a4faf32429c22ecafaf888f8531f8be18600b4a31b8302a4fb47eac8b8c.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_Amusement", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": "4569d7c25d76911c246195182a516d14e32b962e84727e9d3dd629620d326b29", "generation_seconds_batch": 17.837927926098928, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2845546007156372, "target_z": -0.22265622584898564, "ce": 6.165581703186035, "genuineness": 4.570107460021973, "identity": 0.5996513962745667, "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_Amusement/6b973c750e3616c70f28663c29496a0c74bea4a87dff4bad65cadc5394b99131.mp3" }, { "id": "emo_Amusement-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-0", "key": "6b9e3b17d55d7d7290d6325b13816504e54ee1b350c5d2c570e2418136d0e9be", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "cc859669371f7f3deace0ea0dcd72c4fd329bbc94f853163a8175966ec0a0ec2", "generation_seconds_batch": 22.622653793892823, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2843918800354004, "target_z": 0.9296875311279741, "ce": 6.062326908111572, "genuineness": 4.331617832183838, "identity": 0.7263586521148682, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/6b9e3b17d55d7d7290d6325b13816504e54ee1b350c5d2c570e2418136d0e9be.mp3" }, { "id": "emo_Amusement-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-1", "key": "6ba0a5ec476224bbf35348a9ba286b43128172ccedc2b513012282fceb3f1a07", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "775c4e8d5a4353d9e31dee0ccd3242a7a7f595d1fb7e335cef7c3f930be33730", "generation_seconds_batch": 17.78785705100745, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7960102558135986, "target_z": 2.6718750193208116, "ce": 5.974957466125488, "genuineness": 3.886019229888916, "identity": 0.5309938192367554, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/6ba0a5ec476224bbf35348a9ba286b43128172ccedc2b513012282fceb3f1a07.mp3" }, { "id": "emo_Amusement-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-0", "key": "6bb7ca84192190d6ba2fdeb7c18043df9e054f889ce1894ec7ebaf5837c014eb", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De deur staat nog open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "c76e02168e52863e5907a520a2eff4b898adcc7d3eb2f896ee20a25ecf0be41b", "generation_seconds_batch": 20.624441556050442, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.267282724380493, "target_z": 2.0624999914129725, "ce": 6.1020402908325195, "genuineness": 4.3504462242126465, "identity": 0.25736722350120544, "hypothesis": "De deur staat nog open? Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/6bb7ca84192190d6ba2fdeb7c18043df9e054f889ce1894ec7ebaf5837c014eb.mp3" }, { "id": "emo_Amusement-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-1", "key": "6c4942ddda656a00ae0c3b7a212b9760c5a6c9a0f1d20230b0814e7928d367bd", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I found the little box.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It was beside the old window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "954f716cd5ff700dad4eee25b9756cb13bab19d3af6823926c1ceef7776a0f11", "generation_seconds_batch": 21.80685907509178, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7317767143249512, "target_z": 1.4453125547422991, "ce": 6.181467056274414, "genuineness": 4.293961524963379, "identity": 0.1625489890575409, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/6c4942ddda656a00ae0c3b7a212b9760c5a6c9a0f1d20230b0814e7928d367bd.mp3" }, { "id": "emo_Amusement-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-1", "key": "6c8d4cb2628f0e29fb64b172a21269ac1dc180ac4547d23c509f30ca8f4523cd", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I found the little box.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It was beside the old window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "6fa5f9a09fb3096904ed07ebaf0eafe1179d27fd9fa60865106310705b8562cb", "generation_seconds_batch": 16.29742532898672, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4570822715759277, "target_z": 2.281249909836213, "ce": 6.221180438995361, "genuineness": 3.9299514293670654, "identity": 0.20189674198627472, "hypothesis": "I found the little box. It was beside the old window. We can look inside together,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/6c8d4cb2628f0e29fb64b172a21269ac1dc180ac4547d23c509f30ca8f4523cd.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": "6cb76238334a8587d998fafb26671db8c0b7a62594f88ebbca5200a80dc0399d", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e62101ea680591a6461558ad9379b16a35a2624ed6a8b59b1c4ce9e37ad90865", "generation_seconds_batch": 15.09112862101756, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6843267679214478, "target_z": 1.3906250064402705, "ce": 6.372091293334961, "genuineness": 4.143336772918701, "identity": 0.4836078882217407, "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_Amusement/6cb76238334a8587d998fafb26671db8c0b7a62594f88ebbca5200a80dc0399d.mp3" }, { "id": "emo_Amusement-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-1", "key": "6ddf82fbbab8de81d08d1b95623ba8b2be851a7a8ed8512e2bf30aa0e937f902", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "cf4a16bf3bf600115d858e6c5fcde6e72cf7b00247c7744056655a96ae4d382b", "generation_seconds_batch": 24.30096785002388, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.901240587234497, "target_z": 1.6406249720921613, "ce": 6.078212261199951, "genuineness": 4.093128204345703, "identity": 0.46890270709991455, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/6ddf82fbbab8de81d08d1b95623ba8b2be851a7a8ed8512e2bf30aa0e937f902.mp3" }, { "id": "emo_Amusement-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-0", "key": "6f3e481e8a0ec4ab662f7e7692656387de723ca109c8341adbfd43c9656f4342", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "d71c66292f82a7e5cc0e622d53aa8f835d6718bc2ff24364779b8b4cbbd4dd07", "generation_seconds_batch": 24.617716255015694, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6336503028869629, "target_z": 0.17968749677986476, "ce": 6.252951145172119, "genuineness": 4.444586753845215, "identity": 0.746289849281311, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/6f3e481e8a0ec4ab662f7e7692656387de723ca109c8341adbfd43c9656f4342.mp3" }, { "id": "emo_Amusement-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-1", "key": "6fab798c3ed774403df5ef2284bf239f17bc267855812c2daf2bd4307d3cda88", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "569f39e03169c57add3512d3a10892abc2916c37c0b5932c70cd06e37ea9dde6", "generation_seconds_batch": 23.402226174017414, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8198978900909424, "target_z": 1.5468749677986475, "ce": 6.3641486167907715, "genuineness": 4.2751336097717285, "identity": 0.3555867075920105, "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_Amusement/6fab798c3ed774403df5ef2284bf239f17bc267855812c2daf2bd4307d3cda88.mp3" }, { "id": "emo_Amusement-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-1", "key": "70215809f2c301d2c88e01da355eaa4fd8e8cf7d40a85649fa830e5ef20fcfca", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "ebe4d8ddaec3d0dce5aef13875f5932b385499c5023d84079d41cdefde7e0da0", "generation_seconds_batch": 23.422579201986082, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0368118286132812, "target_z": 1.7968750708429755, "ce": 5.903473377227783, "genuineness": 3.8546390533447266, "identity": 0.5764651298522949, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/70215809f2c301d2c88e01da355eaa4fd8e8cf7d40a85649fa830e5ef20fcfca.mp3" }, { "id": "emo_Amusement-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-0", "key": "70de13126bb608c69eae35dbc4ab8a7df1adab79e8f8fba3bc3c512f5d3da049", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "40d53ce4cfbe0fe65585213eb5fb4d63b19d19b27d405b8848c2b7c18073f901", "generation_seconds_batch": 18.04508306796197, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7656694650650024, "target_z": 1.484375010733784, "ce": 6.252951145172119, "genuineness": 4.2751336097717285, "identity": 0.42335617542266846, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/70de13126bb608c69eae35dbc4ab8a7df1adab79e8f8fba3bc3c512f5d3da049.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": "70fd251971340f5762e9fd43868556f454600193874d1c6a64fa90900b320145", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "48c231f305183758cd4c3100788e4570190dcfe6fb978f5adae993c8efe4a5d7", "generation_seconds_batch": 27.29935980506707, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3318417072296143, "target_z": 0.9843749420375656, "ce": 6.173524379730225, "genuineness": 4.105680465698242, "identity": 0.6698561310768127, "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_Amusement/70fd251971340f5762e9fd43868556f454600193874d1c6a64fa90900b320145.mp3" }, { "id": "emo_Amusement-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-1", "key": "72174a15a79d88efa0f16ccdefb3ea8ec8ce4cda5023ae85b167d37237fd4d71", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I found the little box.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It was beside the old window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "cc4a5a08ca3427799a46e9b4be068df682d8e88e417dfa94f1d532822c22c208", "generation_seconds_batch": 20.536168513004668, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6468818187713623, "target_z": 2.4999998282594533, "ce": 6.229123115539551, "genuineness": 3.8295347690582275, "identity": 0.5141071081161499, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/72174a15a79d88efa0f16ccdefb3ea8ec8ce4cda5023ae85b167d37237fd4d71.mp3" }, { "id": "emo_Amusement-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-1", "key": "72500d85ae18a395e9ec6ef038a42198740ade29e16a1a10924f58c487518701", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "6d89653daaa4ac7750a23f7ccfd4877ab5023e3e31e54eb761b7a3a44e429267", "generation_seconds_batch": 17.67427121894434, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.47063946723938, "target_z": 2.296875002146757, "ce": 6.117925643920898, "genuineness": 4.099404335021973, "identity": 0.660347580909729, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/72500d85ae18a395e9ec6ef038a42198740ade29e16a1a10924f58c487518701.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": "7261a9e61e11da3e293804ad74621dda5806a7c57884d4a4c0594fe7885fb622", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0ad4e28b74d6ab499bf8d9b23ee28973e68e5fb1a9881e7626e6773bbd20379c", "generation_seconds_batch": 22.33729331404902, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3350682258605957, "target_z": 2.140624903395943, "ce": 6.062326908111572, "genuineness": 4.256305694580078, "identity": 0.5505626797676086, "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_Amusement/7261a9e61e11da3e293804ad74621dda5806a7c57884d4a4c0594fe7885fb622.mp3" }, { "id": "emo_Amusement-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-0", "key": "72fd7d41122a6d31a764a048a6422ce536d385ebb580373b6120fa6b03685cc3", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "ade59080e5329f775c94701a341f8a8da08634c3920afb2da237e50c9260f610", "generation_seconds_batch": 23.51359774102457, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6775482892990112, "target_z": 1.382812597677436, "ce": 6.1020402908325195, "genuineness": 3.8797430992126465, "identity": 0.4124113619327545, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/72fd7d41122a6d31a764a048a6422ce536d385ebb580373b6120fa6b03685cc3.mp3" }, { "id": "emo_Amusement-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-1", "key": "732c2ff77899bf143cdff531f40c9e9683fd472e981e74a9d7056ce2c2e79721", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "05f04c7c963043043531cbba10a7b974c64748c4bcf8064aa16768af3358ece0", "generation_seconds_batch": 24.01405820308719, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.375739574432373, "target_z": 2.1874999055426994, "ce": 6.141753673553467, "genuineness": 4.337893962860107, "identity": 0.5683832168579102, "hypothesis": "J'ai trouvé la 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_Amusement/732c2ff77899bf143cdff531f40c9e9683fd472e981e74a9d7056ce2c2e79721.mp3" }, { "id": "emo_Amusement-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-0", "key": "7390a840d2a4cf10561f6c0d1cb9f2c8bdddc96ebf647744cb91ec2bbba6d9fa", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "aea5ed4a9352c469f8c671874941ed6d7b3e3fd05ac8034e9667c49b7230a2cc", "generation_seconds_batch": 23.956850653048605, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9283548593521118, "target_z": 1.6718750193208114, "ce": 6.292664527893066, "genuineness": 4.300237655639648, "identity": 0.41937482357025146, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/7390a840d2a4cf10561f6c0d1cb9f2c8bdddc96ebf647744cb91ec2bbba6d9fa.mp3" }, { "id": "emo_Amusement-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-0", "key": "73ebd46ef04c34806cd7e8876595c662b383a49e5d906e92e72a5458725b1fbc", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "0fa17e4e54ca1ad55b4225dc2ea3f5ea2cc9a80c08d91763b326460250898421", "generation_seconds_batch": 25.04123555996921, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1994972229003906, "target_z": 1.9843750794300028, "ce": 5.824047088623047, "genuineness": 3.5690791606903076, "identity": 0.5970311760902405, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/73ebd46ef04c34806cd7e8876595c662b383a49e5d906e92e72a5458725b1fbc.mp3" }, { "id": "emo_Amusement-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-0", "key": "73f2b3b65769d3b34542972656e4bf66eec4e0585d6a9af6ae65812277c7033f", "bucket": "emo_Amusement", "phase": "wording", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "241f51f570e36d93dc9d5993d2853a0ea233734e3a7860630981db556897d570", "generation_seconds_batch": 16.289099897025153, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.023417353630066, "target_z": 0.628906221555472, "ce": 6.308549880981445, "genuineness": 4.268857479095459, "identity": 0.41956591606140137, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/73f2b3b65769d3b34542972656e4bf66eec4e0585d6a9af6ae65812277c7033f.mp3" }, { "id": "emo_Amusement-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-1", "key": "74dbaad00f2bd102895b1002515722925668a90c67e1291c9ae70df5b2c2c30d", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I found the little box.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It was beside the old window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "7b112f75419c4e2cd15cd6ce4a7bfa145510a1f0aae9458ae4e6acdbcd2da586", "generation_seconds_batch": 21.261982748052105, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1859400272369385, "target_z": 1.968749987119459, "ce": 6.308549880981445, "genuineness": 4.162164688110352, "identity": 0.36593908071517944, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/74dbaad00f2bd102895b1002515722925668a90c67e1291c9ae70df5b2c2c30d.mp3" }, { "id": "emo_Amusement-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-0", "key": "75a90312e41d604ce8a655efd9a0cfe3bbdd46cec014890d4a686c8118ae1c86", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "b88352d1fc83fadad754261634bd4ee52fc56fffe48841361c65b0f12819df0d", "generation_seconds_batch": 20.37081340001896, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8095672130584717, "target_z": 2.687499836846481, "ce": 6.125868320465088, "genuineness": 3.961331605911255, "identity": 0.6215255856513977, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/75a90312e41d604ce8a655efd9a0cfe3bbdd46cec014890d4a686c8118ae1c86.mp3" }, { "id": "emo_Amusement-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-1", "key": "75aad94485e7583ae2f3dcd479c56cdb17fa592b7053513e3c1dec490e8e677b", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I found the little box.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It was beside the old window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "ccbddd7808c59ddcc0e968a2f81a577c0f0e5dd6b79f78ddcb9ccae5412a514a", "generation_seconds_batch": 23.576125795021653, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8809049129486084, "target_z": 1.6171874710187828, "ce": 6.4515180587768555, "genuineness": 4.162164688110352, "identity": 0.33027997612953186, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/75aad94485e7583ae2f3dcd479c56cdb17fa592b7053513e3c1dec490e8e677b.mp3" }, { "id": "emo_Amusement-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-0", "key": "75dc05373e0260ad3f07e9149bfefc0cea8a9319096b1a98d471c5b9fbef3a6f", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "d97031613c3491edd3e440266a4d1788b3a3dc782b1043d966b8ca54c51230ec", "generation_seconds_batch": 24.071870076004416, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.067478060722351, "target_z": 0.6796875654760833, "ce": 6.221180438995361, "genuineness": 4.118232727050781, "identity": 0.4982801079750061, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/75dc05373e0260ad3f07e9149bfefc0cea8a9319096b1a98d471c5b9fbef3a6f.mp3" }, { "id": "emo_Amusement-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-0", "key": "75f7583f4e47aeb2bdb45155e606c1f0c727657188c10fa0f7f552065409ffa3", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De deur staat nog open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "9209dbf3e7620bce0398a73ed49c5c898aa1830b2b4e62ea635bf2b6c5b24995", "generation_seconds_batch": 17.533783124992624, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0774831771850586, "target_z": 1.8437500729897323, "ce": 6.09409761428833, "genuineness": 4.406930446624756, "identity": 0.6577491760253906, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar waar 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_Amusement/75f7583f4e47aeb2bdb45155e606c1f0c727657188c10fa0f7f552065409ffa3.mp3" }, { "id": "emo_Amusement-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-0", "key": "760f94d3397c8148a375ab5cee46c9eb427b247032b12486cee3a91a51e2243e", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "006b3683e8ceec56f14be87d1d49a422f1f8d96e59c52489c8b2a55b6efbbed8", "generation_seconds_batch": 16.828103912994266, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9893618822097778, "target_z": 1.7421875225409467, "ce": 5.7406487464904785, "genuineness": 3.9676074981689453, "identity": 0.6418245434761047, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/760f94d3397c8148a375ab5cee46c9eb427b247032b12486cee3a91a51e2243e.mp3" }, { "id": "emo_Amusement-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-1", "key": "76361655670ce01ca91d736c2834e859c581c480a6088391544ac0c755f9647d", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I found the little box.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It was beside the old window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "d5dc1f1b37fcb766c4ed3c95874d762fc7ae40b78bdeafdacd0b63faa26a00e3", "generation_seconds_batch": 24.063946028938517, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0368118286132812, "target_z": 1.7968750708429755, "ce": 6.324435234069824, "genuineness": 4.457139015197754, "identity": 0.41944098472595215, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/76361655670ce01ca91d736c2834e859c581c480a6088391544ac0c755f9647d.mp3" }, { "id": "emo_Amusement-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-0", "key": "765950bd37b4e7ca8ba6ad0dde69b64cf5571e161a5bb8b6559c4b0ff45470b3", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De deur staat nog open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "95248294aeb964550f0023ed137041c9496c75335553053fe8ad0ebb9c9095a0", "generation_seconds_batch": 22.901566465967335, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2298378944396973, "target_z": 3.1718749506245927, "ce": 5.967014789581299, "genuineness": 4.18099308013916, "identity": 0.17087531089782715, "hypothesis": "De deur 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_Amusement/765950bd37b4e7ca8ba6ad0dde69b64cf5571e161a5bb8b6559c4b0ff45470b3.mp3" }, { "id": "emo_Amusement-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-1", "key": "76cd833f84c613546a82eb67430bf84601a19cc14b832ed9061c468f22ced4af", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "a154200c25465a0dc695573b9142bee7250689bde599dd795bf4aec3aa814b80", "generation_seconds_batch": 21.881724565988407, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7556643486022949, "target_z": 0.32031250322013527, "ce": 6.205295085906982, "genuineness": 4.557555198669434, "identity": 0.6207942962646484, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/76cd833f84c613546a82eb67430bf84601a19cc14b832ed9061c468f22ced4af.mp3" }, { "id": "emo_Amusement-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-1", "key": "76e5ac73541b9db4d3f2f75d3fb065556cd547d0b05a7146bc9afe30ccdb8460", "bucket": "emo_Amusement", "phase": "wording", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "01525c6ee1bf435e81acbeff98cec0b7134dfa221a3843942ce03c3d12343e13", "generation_seconds_batch": 15.499376502004452, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1657670736312866, "target_z": 0.7929687290691209, "ce": 6.173524379730225, "genuineness": 4.337893962860107, "identity": 0.643466591835022, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/76e5ac73541b9db4d3f2f75d3fb065556cd547d0b05a7146bc9afe30ccdb8460.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": "775df70df5d009ceec6d33ec42a24968d0ea740a4f6287483a5866dcb92944bb", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "37f9d76139834cf1334e42bcfbd1f470199df7a17fde3d7a961ae9c120edd82e", "generation_seconds_batch": 21.25579543202184, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8742890954017639, "target_z": 0.4570312365827698, "ce": 5.974957466125488, "genuineness": 4.319066047668457, "identity": 0.6649515628814697, "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_Amusement/775df70df5d009ceec6d33ec42a24968d0ea740a4f6287483a5866dcb92944bb.mp3" }, { "id": "emo_Amusement-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-0", "key": "77929cbb8a52e9a2528c1740d0d8d3ce22c992ffc062a5d315a99c45e4f050fd", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De deur staat nog open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "58a19f4df69b1e4b01b9418705ce093d9cd51b79344e46c43184c0986e09ebb1", "generation_seconds_batch": 23.103367885923944, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6739962100982666, "target_z": 2.531250012880541, "ce": 5.903473377227783, "genuineness": 3.9676074981689453, "identity": 0.3573267161846161, "hypothesis": "De deur 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_Amusement/77929cbb8a52e9a2528c1740d0d8d3ce22c992ffc062a5d315a99c45e4f050fd.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_Amusement", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": "42027b5acb779d59ed76b6eff16079c7d6743f6a67dc72d906816dbef459c456", "generation_seconds_batch": 15.490366781014018, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17440301179885864, "target_z": -0.3496093795618583, "ce": 6.141753673553467, "genuineness": 4.557555198669434, "identity": 0.7262020111083984, "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_Amusement/77962898fb95ddc0e92a153772191fe01482e40f98d2245158cb92652e8a93c1.mp3" }, { "id": "emo_Amusement-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-1", "key": "77ac707b7571dfdfa88ef50abbf04b9efe0cb5a7050b683faabb0f390f8434a4", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "e0fffad9764e70c7fb63d94f8b6f86e649df636a2f1d2199e268154ba7cdc024", "generation_seconds_batch": 21.906306438031606, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.023254632949829, "target_z": 1.7812499785324316, "ce": 6.046441555023193, "genuineness": 4.162164688110352, "identity": 0.5679650902748108, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/77ac707b7571dfdfa88ef50abbf04b9efe0cb5a7050b683faabb0f390f8434a4.mp3" }, { "id": "emo_Amusement-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-0", "key": "77f18a013a775a0c345106c85e3be0bed5a906782843e758bc1bc24af74db3fa", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "fe94383608edf65448b9a035925e5546bba38509d66ac60e448e1739c07449cb", "generation_seconds_batch": 24.04601965995971, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2199954986572266, "target_z": 0.8554686861339843, "ce": 5.903473377227783, "genuineness": 3.660081624984741, "identity": 0.33416175842285156, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/77f18a013a775a0c345106c85e3be0bed5a906782843e758bc1bc24af74db3fa.mp3" }, { "id": "emo_Amusement-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-0", "key": "785d43eb926cd70a9bb3cabbaa70b7c422478a502cf5425c7f62ea97074409d0", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De deur staat nog open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "49c9d80f0739296a5833961588ea2e125bd1e32425f1aa16b94ff002596f6150", "generation_seconds_batch": 22.26219158398453, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.541977047920227, "target_z": 1.2265624989266215, "ce": 6.157639026641846, "genuineness": 4.432034492492676, "identity": 0.13240478932857513, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/785d43eb926cd70a9bb3cabbaa70b7c422478a502cf5425c7f62ea97074409d0.mp3" }, { "id": "emo_Amusement-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-0", "key": "786c5c78b67f1845bcaf8ee8727f703837f8441277aaaee4d802ac0d82afe92d", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The door is still open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "69b0a82943363dcfdd092b0ecab022c60d2ee97283ac308d7b6ea674a7ef21f2", "generation_seconds_batch": 22.685833358904347, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.836681604385376, "target_z": 2.718750021467568, "ce": 6.229123115539551, "genuineness": 3.7040140628814697, "identity": 0.49455583095550537, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/786c5c78b67f1845bcaf8ee8727f703837f8441277aaaee4d802ac0d82afe92d.mp3" }, { "id": "emo_Amusement-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-1", "key": "78aca16f231ff7ea4a8062181b7ff02ba1a04c847068a8bb3d7cf087f4651b63", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I found the little box.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It was beside the old window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4dfb2e8104cee448605ed4e968f13a890f53a51b215d45fb2c569d6e6a1e77fd", "generation_seconds_batch": 18.33543976699002, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.985809803009033, "target_z": 2.890624937744052, "ce": 6.165581703186035, "genuineness": 4.124508857727051, "identity": 0.48459291458129883, "hypothesis": "I found the little fox. 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_Amusement/78aca16f231ff7ea4a8062181b7ff02ba1a04c847068a8bb3d7cf087f4651b63.mp3" }, { "id": "emo_Amusement-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-0", "key": "78b1f252923fe1a76d0a95d65945f31a1c2a38fb8cdff05771dbe4514d3d98a1", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "f225144bb17efce4f26d4b52645f7df39e4a51e0ae1ac313cbe2e67c3dca9e93", "generation_seconds_batch": 17.76061723800376, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0368118286132812, "target_z": 1.7968750708429755, "ce": 6.038498878479004, "genuineness": 3.525146961212158, "identity": 0.4890705943107605, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/78b1f252923fe1a76d0a95d65945f31a1c2a38fb8cdff05771dbe4514d3d98a1.mp3" }, { "id": "emo_Amusement-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-0", "key": "78ddc6d9a5861e9eb81d5e451cc236c7073ec15360b6e533459a0e18bc97e15b", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "3f4ab76af997b47d37b5ddc444e38a2eb8f0157583a2601fd8c95dd9f9e787bb", "generation_seconds_batch": 23.227408646955155, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0639259815216064, "target_z": 1.8281249806791886, "ce": 5.871703147888184, "genuineness": 3.8295347690582275, "identity": 0.6330231428146362, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/78ddc6d9a5861e9eb81d5e451cc236c7073ec15360b6e533459a0e18bc97e15b.mp3" }, { "id": "emo_Amusement-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-1", "key": "7900023b1731442c2f51c4530bcb3aaa3b880bcfac4817fa0e685aa7dca9385a", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I found the little box.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It was beside the old window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "ddac73fda1d44f81867b6494b2ba6f8ad019fd2cba031215f97345b3fb8576aa", "generation_seconds_batch": 26.46711249393411, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5113108158111572, "target_z": 2.3437500042935135, "ce": 6.38003396987915, "genuineness": 3.9173994064331055, "identity": 0.3720279633998871, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/7900023b1731442c2f51c4530bcb3aaa3b880bcfac4817fa0e685aa7dca9385a.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_Amusement", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 127, "seconds_generated": 10.16, "mp3_sha256": "09f4abb3b092849d9449f3b33711b22989e07e28de8dabf20b872f5d6bba0f37", "generation_seconds_batch": 16.512283504009247, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8031142950057983, "target_z": 0.3750000515221639, "ce": 6.062326908111572, "genuineness": 4.293961524963379, "identity": 0.7312742471694946, "hypothesis": "De sleutels liggen op de keukentafel. Ik keek in de la en daarna, naast het raam. Neem ze mee als je weggaat.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/794d3b9296e3c4be7c1e4182a2fa3cf095f7d593990763ce0f19c1f5e499a989.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": "79d72e676d941faac76078dd60162b7953a401119beed1e4d6f7186d4238128e", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1376c48b191155eff46b0a0af5f7c1d220da9b82c5f80f0c2486d04bcc27d4b6", "generation_seconds_batch": 17.01973423396703, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5351985692977905, "target_z": 1.2187500901637869, "ce": 6.2767791748046875, "genuineness": 4.406930446624756, "identity": 0.690085768699646, "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_Amusement/79d72e676d941faac76078dd60162b7953a401119beed1e4d6f7186d4238128e.mp3" }, { "id": "emo_Amusement-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-1", "key": "7a672612e4a2b5a542bc6fc52423f02967152aed0048d1cb03435472fa73073f", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "6084cb292161b673a46d41569cd0ca8a8140152e9bcf0b8e6524b6249e8208e3", "generation_seconds_batch": 24.36850266600959, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.297948956489563, "target_z": 0.9453124860460806, "ce": 6.205295085906982, "genuineness": 4.319066047668457, "identity": 0.6365676522254944, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/7a672612e4a2b5a542bc6fc52423f02967152aed0048d1cb03435472fa73073f.mp3" }, { "id": "emo_Amusement-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-1", "key": "7a93cd9e414595d4d5ed39cf2d4ce7d1371de6723d059a38504e1ee22fabadb1", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I found the little box.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It was beside the old window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "999f6c3bdb1f6a8fb9fec5eaf23cf39983314495a829ff09f7dc0126157f7b09", "generation_seconds_batch": 18.355054907035083, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.375739574432373, "target_z": 2.1874999055426994, "ce": 6.308549880981445, "genuineness": 3.9676074981689453, "identity": 0.3799518942832947, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/7a93cd9e414595d4d5ed39cf2d4ce7d1371de6723d059a38504e1ee22fabadb1.mp3" }, { "id": "emo_Amusement-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-1", "key": "7aa6c3e761c7a11d79dc98e9a6881be8acf9f095ae8c12e14efcde400636264b", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "d00892182419ab46b462fd0656731b6f3208f4dfd62db490aff959970ccfe021", "generation_seconds_batch": 24.795233883080073, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6165412664413452, "target_z": 1.3125000944573006, "ce": 6.268836498260498, "genuineness": 4.419482707977295, "identity": 0.5716590881347656, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient. Ah!", "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_Amusement/7aa6c3e761c7a11d79dc98e9a6881be8acf9f095ae8c12e14efcde400636264b.mp3" }, { "id": "emo_Amusement-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-0", "key": "7b2c770fb08226eed26c06bddfd006991f022e756e2a1a3b76cbafd5a43451ac", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "51aee4e5027479b1cdd0f59c1fa07374cc1c7fe110351d123be095fe6ecbf096", "generation_seconds_batch": 25.37163722398691, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.701110363006592, "target_z": 2.562499922716754, "ce": 5.863759994506836, "genuineness": 4.068024158477783, "identity": 0.03723069652915001, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/7b2c770fb08226eed26c06bddfd006991f022e756e2a1a3b76cbafd5a43451ac.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": "7b4f9f60493348583f71519eb7052c6909ebf1bf35e05dcfa2947ae7d8384789", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ac9734067ea93c7425d4de38559472f318c5c4ed37c7b07210dbc130a5479b4a", "generation_seconds_batch": 20.614351495052688, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2130541801452637, "target_z": 1.999999896955672, "ce": 6.1894097328186035, "genuineness": 4.218649387359619, "identity": 0.6057233810424805, "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_Amusement/7b4f9f60493348583f71519eb7052c6909ebf1bf35e05dcfa2947ae7d8384789.mp3" }, { "id": "emo_Amusement-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-1", "key": "7b945aa87889e88cddb49d5fedcb4e942e434c0cc35f24d217b27d98d32d9c2a", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "94742bd52888229b06ab7e8f6701e821f9f38f1f58383e7998e4b5a8ec646f20", "generation_seconds_batch": 17.245006195036694, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.365734577178955, "target_z": 1.0234375354214877, "ce": 6.1894097328186035, "genuineness": 4.268857479095459, "identity": 0.7259073257446289, "hypothesis": "J'ai trouvé la 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_Amusement/7b945aa87889e88cddb49d5fedcb4e942e434c0cc35f24d217b27d98d32d9c2a.mp3" }, { "id": "emo_Amusement-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-1", "key": "7bb56dd31acbcf5a66de2a7958abcc54c40d1925ef6c296cec4b566a2a6cdc07", "bucket": "emo_Amusement", "phase": "wording", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "7f65da750b9eae954b9cdd567b4b5daa967f19d685802033d7db69526fb05058", "generation_seconds_batch": 17.327306136023253, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4538557529449463, "target_z": 1.1249999484778361, "ce": 6.213237762451172, "genuineness": 4.362998008728027, "identity": 0.6038111448287964, "hypothesis": "J'ai trouvé la 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_Amusement/7bb56dd31acbcf5a66de2a7958abcc54c40d1925ef6c296cec4b566a2a6cdc07.mp3" }, { "id": "emo_Amusement-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-0", "key": "7c6b672ea8968e4399f754a304a96f3941c31c38ffd818c64bdb335110aa1c87", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The door is still open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "71a45e499dc2bdc7e98a38148d4b8029935722a2b86fc34680911751205e9bd7", "generation_seconds_batch": 16.07988484890666, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9758048057556152, "target_z": 1.7265625676228402, "ce": 6.332377910614014, "genuineness": 3.936227321624756, "identity": 0.26232215762138367, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/7c6b672ea8968e4399f754a304a96f3941c31c38ffd818c64bdb335110aa1c87.mp3" }, { "id": "emo_Amusement-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-1", "key": "7cad247f4a92099209f83241eca0356935482d07ab8a10e4bd0cc8ecb674aee9", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "eec17aa13def33ccc6d9d18df7aec9fa6cdedbe9589304660b06f079b5080bec", "generation_seconds_batch": 19.991976664983667, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9486905336380005, "target_z": 1.69531252039419, "ce": 6.0146708488464355, "genuineness": 3.998987913131714, "identity": 0.6731659770011902, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/7cad247f4a92099209f83241eca0356935482d07ab8a10e4bd0cc8ecb674aee9.mp3" }, { "id": "emo_Amusement-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-1", "key": "7cafabda4e773c62645c6d5a3abf82b1b408bbbae5a8d055db0085f3154f1410", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I found the little box.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It was beside the old window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "3b70083ce84d914be00186d4f853a0050d4980ecd3fc4f879e4a432188a3a622", "generation_seconds_batch": 23.26608707604464, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6875531673431396, "target_z": 2.5468748304062103, "ce": 6.149696350097656, "genuineness": 3.6287014484405518, "identity": 0.5489878058433533, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/7cafabda4e773c62645c6d5a3abf82b1b408bbbae5a8d055db0085f3154f1410.mp3" }, { "id": "emo_Amusement-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-0", "key": "7d5b458ae7d834f4a6703cb43952db138314bf4b7900034aa6176467d24e5610", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The door is still open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "875b6830bdb7806171eeb7c99f0565e5159a6a7fd1e9ac5e24da51b632925f7c", "generation_seconds_batch": 23.616935844998807, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5790963172912598, "target_z": 2.4218749162764834, "ce": 6.141753673553467, "genuineness": 3.5722172260284424, "identity": 0.45723533630371094, "hypothesis": "The 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_Amusement/7d5b458ae7d834f4a6703cb43952db138314bf4b7900034aa6176467d24e5610.mp3" }, { "id": "emo_Amusement-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-1", "key": "7dbe8f09f2f38526c707c46926f0977d5d3ef1fe8188bdec60bc5eee36261082", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "e0b78b9f2fec703cfa9b3ba3bc9444acfd7fb08599f166abcf379dca3865764f", "generation_seconds_batch": 22.575771374977194, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7453337907791138, "target_z": 1.4609375096604058, "ce": 6.197352409362793, "genuineness": 4.231201171875, "identity": 0.5639780759811401, "hypothesis": "J'ai trouvé la 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_Amusement/7dbe8f09f2f38526c707c46926f0977d5d3ef1fe8188bdec60bc5eee36261082.mp3" }, { "id": "emo_Amusement-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-1", "key": "7dc319f300b6856c9794c9a2bd65e31b6963078328f2d4f79058bf1a870e78be", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "bd4eacc90bb241dbd9c605378ce074718a030b9d9ae2d7aa43f29f9477414b05", "generation_seconds_batch": 21.910750183975324, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3148953914642334, "target_z": 0.9648437827380417, "ce": 6.372091293334961, "genuineness": 3.9173994064331055, "identity": 0.3259778320789337, "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_Amusement/7dc319f300b6856c9794c9a2bd65e31b6963078328f2d4f79058bf1a870e78be.mp3" }, { "id": "emo_Amusement-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-1", "key": "7ecf619ce6892e80981707ad6d5a47044c37cb1f8d8825af1548799c86712b22", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "a45bd5dc2cd896d5586138b2933910abdb63cfe8d8292293ab122d1d78a2b60a", "generation_seconds_batch": 21.720479234005325, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.972252607345581, "target_z": 2.8749998454335084, "ce": 5.982900142669678, "genuineness": 4.049196243286133, "identity": 0.5033630132675171, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/7ecf619ce6892e80981707ad6d5a47044c37cb1f8d8825af1548799c86712b22.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_Amusement", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": "98edadc2a72c9eef9692e9197b073a9b094516c658761da0e6fa0a209a7c1ffa", "generation_seconds_batch": 15.698369250050746, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8437855839729309, "target_z": 0.4218749849727022, "ce": 6.403861999511719, "genuineness": 4.369274139404297, "identity": 0.4308459460735321, "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_Amusement/7f6fce1a6f733719f45a363f28fee4e24b2f07a3396aa07b42392913d7c24239.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": "80409667320fd41149ce6aca762676cfb04460dad2a52f24c2ded6418a7f451a", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "679477b9a3b869b78176e3c34e04d41fe82b4f9b4702aae85d30186c8bab805e", "generation_seconds_batch": 23.69501207000576, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8470121622085571, "target_z": 1.5781250150272979, "ce": 6.125868320465088, "genuineness": 4.055472373962402, "identity": 0.5851207375526428, "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_Amusement/80409667320fd41149ce6aca762676cfb04460dad2a52f24c2ded6418a7f451a.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_Amusement", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": "a91181954e621b72a8536f3f5c55c43212266e8b696c63fe4de8445e4cc60d29", "generation_seconds_batch": 17.153998289024457, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.901240587234497, "target_z": 1.6406249720921613, "ce": 6.213237762451172, "genuineness": 4.457139015197754, "identity": 0.5416042804718018, "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_Amusement/80c2597a6b8f43b5338a6b37d654868d679f46ded48514b42837ab18fba327ad.mp3" }, { "id": "emo_Amusement-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-1", "key": "80d1d2e2e419bf14db54b120a7d09ef189f8c8d21816071e2b6b23dc0e5f6b95", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I found the little box.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It was beside the old window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8898c9f84f8bf892a0b4731f3991ff11030cc718469e739116ca32729e0586df", "generation_seconds_batch": 18.731730713974684, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7724480628967285, "target_z": 1.492187556889056, "ce": 6.3641486167907715, "genuineness": 4.250029563903809, "identity": 0.4856971204280853, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/80d1d2e2e419bf14db54b120a7d09ef189f8c8d21816071e2b6b23dc0e5f6b95.mp3" }, { "id": "emo_Amusement-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-0", "key": "80e26ae15d5f0127370fcb7833bc9bf5d37556a97a1d71ceb971d9d73fc349f8", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "693259067e34a2c82f367b801a8f6f0da2370f45cdc7bd27788d61fafd6c86b6", "generation_seconds_batch": 22.56086375808809, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8266764879226685, "target_z": 1.5546875139539194, "ce": 6.173524379730225, "genuineness": 4.507347106933594, "identity": 0.5423678159713745, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/80e26ae15d5f0127370fcb7833bc9bf5d37556a97a1d71ceb971d9d73fc349f8.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": "80f5faa16a90ed7716307fb7ca3142b92139e10bc90561be031b9b903dc3be4d", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1a7b2351e7f9fe4df7bb93a4607d246d7f175ba8ee7b88824f4bffdeed159b00", "generation_seconds_batch": 15.213280186988413, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8605692386627197, "target_z": 1.5937499699454043, "ce": 6.133810997009277, "genuineness": 4.356721878051758, "identity": 0.7489811182022095, "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_Amusement/80f5faa16a90ed7716307fb7ca3142b92139e10bc90561be031b9b903dc3be4d.mp3" }, { "id": "emo_Amusement-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-1", "key": "81636dc23777d8b92babfdaedaa736ac3130aed172fe6fe5c2021eea0355a4ba", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "afaec93a9b50c1e60f5a2138558f0e16d648a1ece6e4bcf9bcfc13451a0bce15", "generation_seconds_batch": 23.427003188058734, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2130541801452637, "target_z": 1.999999896955672, "ce": 6.2767791748046875, "genuineness": 4.017816066741943, "identity": 0.4244672656059265, "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_Amusement/81636dc23777d8b92babfdaedaa736ac3130aed172fe6fe5c2021eea0355a4ba.mp3" }, { "id": "emo_Amusement-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-0", "key": "817efdb8953b916044a3199919c36628ca22c70ef2f1057275ecf973f2769036", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The door is still open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1f4cf76c69257618bc53b905cd942deb900b011c63ee036211bf0370a226979e", "generation_seconds_batch": 17.65625928598456, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.497753620147705, "target_z": 2.32812491198297, "ce": 6.038498878479004, "genuineness": 3.6663577556610107, "identity": 0.3471628427505493, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/817efdb8953b916044a3199919c36628ca22c70ef2f1057275ecf973f2769036.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": "81851bef8251343350b10c2d9a5576ed1b7da7992c5d310aff48e918adedd82b", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "aa3cbea464960d588c43ee8e075a7a25ef0bef71f98dba7425ef29f1b66c7667", "generation_seconds_batch": 17.906031823018566, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6097626686096191, "target_z": 1.3046875483020286, "ce": 6.109982967376709, "genuineness": 4.3504462242126465, "identity": 0.5745379328727722, "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_Amusement/81851bef8251343350b10c2d9a5576ed1b7da7992c5d310aff48e918adedd82b.mp3" }, { "id": "emo_Amusement-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-0", "key": "81dd581073da585d8ad6cfa292f70920a21ccd0d7aee48388031f32f513b52a9", "bucket": "emo_Amusement", "phase": "wording", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "ba831188bf6820655500c8c74fcfe4709fb4524a81c6946ee65832c0dd538157", "generation_seconds_batch": 20.07572298590094, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.358955979347229, "target_z": 1.015624989266216, "ce": 6.0305562019348145, "genuineness": 4.281409740447998, "identity": 0.6872713565826416, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/81dd581073da585d8ad6cfa292f70920a21ccd0d7aee48388031f32f513b52a9.mp3" }, { "id": "emo_Amusement-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-0", "key": "81dd87d234234b6d6514e9ce739810f41b96384ccf9b42aa49a0368aee63aa43", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f2118e5752f085a3c616027d627a4c28c9ef374a943bc22e36189ee91a9f99cc", "generation_seconds_batch": 24.40829053998459, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5758699178695679, "target_z": 1.2656250923105437, "ce": 6.054384231567383, "genuineness": 4.111956596374512, "identity": 0.6347008347511292, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/81dd87d234234b6d6514e9ce739810f41b96384ccf9b42aa49a0368aee63aa43.mp3" }, { "id": "emo_Amusement-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-1", "key": "82211afddfe43453d5e46a20a7da119573f10f9448effe4e408f5eed50760402", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I found the little box.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It was beside the old window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "640bffc80de0bc4fec8706d08604362dadeef5c2eff24f89666af9535de9468c", "generation_seconds_batch": 21.815514944959432, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.972252607345581, "target_z": 2.8749998454335084, "ce": 6.268836498260498, "genuineness": 3.8420867919921875, "identity": 0.4485514163970947, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/82211afddfe43453d5e46a20a7da119573f10f9448effe4e408f5eed50760402.mp3" }, { "id": "emo_Amusement-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-1", "key": "82deccc75ce4da8f2ad979a6a7f1943d92ae79939b8272ac6a844cdce89d8c94", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I found the little box.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It was beside the old window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "325d478b16d2dc9c1a171fbc9bdde8382157ed656c7ede10b9e5dd5633c03283", "generation_seconds_batch": 24.358915442950092, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4299681186676025, "target_z": 2.25, "ce": 6.205295085906982, "genuineness": 4.143336772918701, "identity": 0.4208500385284424, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/82deccc75ce4da8f2ad979a6a7f1943d92ae79939b8272ac6a844cdce89d8c94.mp3" }, { "id": "emo_Amusement-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-1", "key": "83135d9aa977991f5a6a9fd96b371caa6a1a319f24a30c8072e9e0d4c09b3e98", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "9da7178e7b04af6f0f4b3ab64aa51643d984a8e0c57e275ed513ff5d057f905a", "generation_seconds_batch": 24.250329770962708, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7521123886108398, "target_z": 1.4687500558156776, "ce": 6.181467056274414, "genuineness": 4.105680465698242, "identity": 0.4317019283771515, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/83135d9aa977991f5a6a9fd96b371caa6a1a319f24a30c8072e9e0d4c09b3e98.mp3" }, { "id": "emo_Amusement-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-1", "key": "831a33e3b0aaead1d28b7f96ada88a74a764132c4c16acd182e4cb9660b8b2fc", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "0f615e8db41c035291d19487b841562c0e7cf88e9e62bfa9b90a8c0ef7d69954", "generation_seconds_batch": 22.380848158034496, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5284199714660645, "target_z": 1.210937544008515, "ce": 6.205295085906982, "genuineness": 4.369274139404297, "identity": 0.6338316202163696, "hypothesis": "J'ai trouvé la 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_Amusement/831a33e3b0aaead1d28b7f96ada88a74a764132c4c16acd182e4cb9660b8b2fc.mp3" }, { "id": "emo_Amusement-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-1", "key": "83cc9e8c0847b77fa6a11f10e07a045f92f208e886d08bfe098e268273a85565", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I found the little box.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It was beside the old window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "8c0df498e8777a790d35020e93d9ef933e1934184f1c0274236effb1f530ba8a", "generation_seconds_batch": 16.29742532898672, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5655391216278076, "target_z": 2.40624982396594, "ce": 6.356205940246582, "genuineness": 4.243753433227539, "identity": 0.3679155707359314, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/83cc9e8c0847b77fa6a11f10e07a045f92f208e886d08bfe098e268273a85565.mp3" }, { "id": "emo_Amusement-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-0", "key": "83fdd41cf2a6ebaddf6bd3b7649261b022247d7511d969b32926da4ea4428fe0", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The door is still open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "c352c478bd7983f9ce40a76552ac131d377628a9fc1da3afa670a87fad090af3", "generation_seconds_batch": 23.45515908394009, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.497753620147705, "target_z": 2.32812491198297, "ce": 6.229123115539551, "genuineness": 3.747946262359619, "identity": 0.33381855487823486, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/83fdd41cf2a6ebaddf6bd3b7649261b022247d7511d969b32926da4ea4428fe0.mp3" }, { "id": "emo_Amusement-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-0", "key": "840b5c0e6d5c728531d3712d83f5629e6337e76edc0d660e874938dfff9c176d", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "525550b742722b97992956a2b52acd85ddeb9ac91d1b61c2e71cc9a4edce3725", "generation_seconds_batch": 21.654846042045392, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.084261655807495, "target_z": 1.8515624817525669, "ce": 6.0305562019348145, "genuineness": 3.8671910762786865, "identity": 0.25224798917770386, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/840b5c0e6d5c728531d3712d83f5629e6337e76edc0d660e874938dfff9c176d.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": "8499bdf78df48b4ee0348074b0aed6e20dcf5bf4e27526b7b14365722a2b43d4", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d78f60514df029a4596c5f131f806ce4e26efdaa2e53608020a76548927dd442", "generation_seconds_batch": 20.12339791096747, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9893618822097778, "target_z": 1.7421875225409467, "ce": 6.38797664642334, "genuineness": 4.369274139404297, "identity": 0.5553591847419739, "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_Amusement/8499bdf78df48b4ee0348074b0aed6e20dcf5bf4e27526b7b14365722a2b43d4.mp3" }, { "id": "emo_Amusement-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-0", "key": "849cf955738e7c0b075ea17cde501fde68b07b2e85ee67e68c5ef2d267bd0121", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "f4793271be27f91a1ad74cf4c4dbe53e212df5bc2740f3af42cba54d2b920361", "generation_seconds_batch": 16.488341031013988, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9793567657470703, "target_z": 0.5781250150272979, "ce": 6.022613525390625, "genuineness": 4.093128204345703, "identity": 0.44993942975997925, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/849cf955738e7c0b075ea17cde501fde68b07b2e85ee67e68c5ef2d267bd0121.mp3" }, { "id": "emo_Amusement-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-1", "key": "849d53cc6a96332ed3dc8615aa0bce6654549dd50fbd4f07a24ec6e2cb656068", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dfe5ae8878cadb6c06d4a653ee922343ed152bdc534fd008eb9e964f5e3b4e42", "generation_seconds_batch": 23.649470258969814, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6875531673431396, "target_z": 2.5468748304062103, "ce": 5.982900142669678, "genuineness": 3.9425034523010254, "identity": 0.15090662240982056, "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_Amusement/849d53cc6a96332ed3dc8615aa0bce6654549dd50fbd4f07a24ec6e2cb656068.mp3" }, { "id": "emo_Amusement-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-0", "key": "84b17358a4a6e111b17ae5eb623024ffc81159a57439e2959c48eae2bb837bb9", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a62bb920e26115b7f74ace5de9c05d76655d3a892d71a64ca6136962ad09bfe6", "generation_seconds_batch": 22.39655245002359, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5013056993484497, "target_z": 1.1796874967798647, "ce": 6.41180419921875, "genuineness": 4.507347106933594, "identity": 0.7747849822044373, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/84b17358a4a6e111b17ae5eb623024ffc81159a57439e2959c48eae2bb837bb9.mp3" }, { "id": "emo_Amusement-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-0", "key": "84bde6c0858167aa4efd292f5fc53878f99d8f0f6e3a5b5c61e2c89d4454043e", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The door is still open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "1479d197998089f2d6e3b019d8fb66e6ca83afe7a0af4cec967f46d2a9688d8b", "generation_seconds_batch": 21.74795415601693, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.104597330093384, "target_z": 1.8749999828259454, "ce": 6.2767791748046875, "genuineness": 3.8797430992126465, "identity": 0.3988567590713501, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/84bde6c0858167aa4efd292f5fc53878f99d8f0f6e3a5b5c61e2c89d4454043e.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": "858d3a17814eaee5921106f61f28a33e0823f4387cd64ee5b6a34e0ccc81dd31", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0527112825adf7a739300f5c437f4e8962f031747fbc55d64a70ded3486b094f", "generation_seconds_batch": 20.614351495052688, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3079540729522705, "target_z": 2.1093749935597295, "ce": 6.197352409362793, "genuineness": 4.356721878051758, "identity": 0.6579864025115967, "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_Amusement/858d3a17814eaee5921106f61f28a33e0823f4387cd64ee5b6a34e0ccc81dd31.mp3" }, { "id": "emo_Amusement-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-0", "key": "85cbefcaeb1610aac40a0e7859c9770c356ebef79221f650bcb81599cf0aaab1", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "5431627ec5c332d2ddb83980583de4563306a220434b20131733dff50b47d36f", "generation_seconds_batch": 22.5930978290271, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4028539657592773, "target_z": 2.218750090163787, "ce": 5.395142555236816, "genuineness": 3.515732765197754, "identity": 0.4026980996131897, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/85cbefcaeb1610aac40a0e7859c9770c356ebef79221f650bcb81599cf0aaab1.mp3" }, { "id": "emo_Amusement-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-0", "key": "8696f80d9e8550298cc0e1df3fcfee92e421f4210eb3de90adf29d46f592c624", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The door is still open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "474644514a8c1e24e6f238b638e9bf0f6ed72e1294b24bf287f4ba9a4937688b", "generation_seconds_batch": 24.23870539094787, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1723828315734863, "target_z": 1.9531248948089153, "ce": 6.165581703186035, "genuineness": 3.9299514293670654, "identity": 0.3113618791103363, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/8696f80d9e8550298cc0e1df3fcfee92e421f4210eb3de90adf29d46f592c624.mp3" }, { "id": "emo_Amusement-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-0", "key": "86d68681b92abee4a6a497e5b13b3f1525afdacda51456c66e247a8b72aabb61", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De deur staat nog open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "caf8d6e7d753357943715e94d62147977ca88ad280a141965298fef9cc0b1d14", "generation_seconds_batch": 22.93507560098078, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0029189586639404, "target_z": 1.7578124774590533, "ce": 6.157639026641846, "genuineness": 4.193545341491699, "identity": 0.33983567357063293, "hypothesis": "De deur staat nog open? Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/86d68681b92abee4a6a497e5b13b3f1525afdacda51456c66e247a8b72aabb61.mp3" }, { "id": "emo_Amusement-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-1", "key": "86f23d113d3bc159947e4cb746e92fad45608f23652be96f89164438ca7318de", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "bca71692531cb81daf92bdf7411a04f673f14d24c7369a1101e6ca2b6f34958e", "generation_seconds_batch": 25.251025289064273, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5080842971801758, "target_z": 1.1875000429351366, "ce": 6.260893821716309, "genuineness": 4.331617832183838, "identity": 0.6153717637062073, "hypothesis": "J'ai trouvé la 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_Amusement/86f23d113d3bc159947e4cb746e92fad45608f23652be96f89164438ca7318de.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": "877c8e492c7fc93ce147713a7e0c6f8a89d3333e82d7d674949f1de61f735d9b", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "285a11ac6ce2dc7eef623425f5620bbdffd0fc5c843728af6f621956bb527a0e", "generation_seconds_batch": 26.821413272991776, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5826483964920044, "target_z": 1.2734375010733785, "ce": 6.038498878479004, "genuineness": 4.061748504638672, "identity": 0.5305600166320801, "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_Amusement/877c8e492c7fc93ce147713a7e0c6f8a89d3333e82d7d674949f1de61f735d9b.mp3" }, { "id": "emo_Amusement-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-0", "key": "87b7227e90a09338441246f580d5697732b09fac8bf03aa018f9f35c668f82f2", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "9d99d5d9171ca41fc915699be612b66d93348ed9c395710f21fc1eef7ff82da1", "generation_seconds_batch": 17.29784470004961, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3860702514648438, "target_z": 1.046875036494866, "ce": 6.149696350097656, "genuineness": 4.68307638168335, "identity": 0.6303948163986206, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/87b7227e90a09338441246f580d5697732b09fac8bf03aa018f9f35c668f82f2.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": "87eb471fafe200a39b7b34dcbbc27ce7f1034c08c5b36e80a0b2fb9b100e0898", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "85a6841767b9950d9b2fc0d9ac0c28d19947b02ccc19938135d6339aaba4a704", "generation_seconds_batch": 19.479360562050715, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.206275701522827, "target_z": 1.9921874881928374, "ce": 6.054384231567383, "genuineness": 3.9425034523010254, "identity": 0.5992061495780945, "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": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/87eb471fafe200a39b7b34dcbbc27ce7f1034c08c5b36e80a0b2fb9b100e0898.mp3" }, { "id": "emo_Amusement-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-1", "key": "87fe28447e236e7ccc933f853b0afcec381190a801baa12055576a8363708394", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "96d101b44b5c24367ab4cd17193444e16a46f24ddb904258a158c75c0c5d8ded", "generation_seconds_batch": 21.96719250897877, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3250632286071777, "target_z": 0.9765625332747309, "ce": 6.229123115539551, "genuineness": 4.319066047668457, "identity": 0.8005128502845764, "hypothesis": "ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/87fe28447e236e7ccc933f853b0afcec381190a801baa12055576a8363708394.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": "881f2d2585e9175d7250ef5840b7cdfca10e9c7e2f75a02a530afd5d00ecf019", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f66ab71e2d2f408ff5fa537cd7567a63d3f1c4f709802bd565de76d458979675", "generation_seconds_batch": 23.69501207000576, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7114410400390625, "target_z": 1.4218750536689209, "ce": 6.308549880981445, "genuineness": 4.250029563903809, "identity": 0.6823886036872864, "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_Amusement/881f2d2585e9175d7250ef5840b7cdfca10e9c7e2f75a02a530afd5d00ecf019.mp3" }, { "id": "emo_Amusement-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-0", "key": "896f27c7ef95a8fbef531c95b614273d5c11e9d784c4b4ac6f730b88a355fd7b", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bde0eb35d62097f53102943b56adb2ba1060181fdab99a33957aecb7f56dfed6", "generation_seconds_batch": 20.060467932955362, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1859400272369385, "target_z": 1.968749987119459, "ce": 6.252951145172119, "genuineness": 4.419482707977295, "identity": 0.5902668237686157, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/896f27c7ef95a8fbef531c95b614273d5c11e9d784c4b4ac6f730b88a355fd7b.mp3" }, { "id": "emo_Amusement-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-1", "key": "897c83f2ac7093f772ec4c81759022226229d1a9566fe0f399e8937dd458c1db", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "557dfb3a8afd3617ff524f2a53abc9f227d03eff1f7a5da664d63b23934607a6", "generation_seconds_batch": 20.339048321940936, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9993669986724854, "target_z": 2.9062500300545957, "ce": 5.967014789581299, "genuineness": 4.18099308013916, "identity": 0.4543376863002777, "hypothesis": "Ik heb het kleine doosje gevonden en stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/897c83f2ac7093f772ec4c81759022226229d1a9566fe0f399e8937dd458c1db.mp3" }, { "id": "emo_Amusement-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-0", "key": "8a2d691431f221b5781fa9419101790fdafff4a9ea91d731766fab8914c7b292", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b9ee9f62aca3dc16cbde87b3146c89b253b25949c85b8fd96dafb210ffbf7d80", "generation_seconds_batch": 22.18319084099494, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8198978900909424, "target_z": 1.5468749677986475, "ce": 6.054384231567383, "genuineness": 4.256305694580078, "identity": 0.7451467514038086, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/8a2d691431f221b5781fa9419101790fdafff4a9ea91d731766fab8914c7b292.mp3" }, { "id": "emo_Amusement-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-0", "key": "8b27d750dcf8135f3c9eeb74939de4c66cdf2a57190cb42e356233c0964a6588", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "7f464ac6f0464dc7337e90cf151e9b4cfaeadee4c5c2f43f9fb1618060937c28", "generation_seconds_batch": 20.840472667943686, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0535953044891357, "target_z": 2.968749849727022, "ce": 6.062326908111572, "genuineness": 4.2374773025512695, "identity": 0.5714831948280334, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/8b27d750dcf8135f3c9eeb74939de4c66cdf2a57190cb42e356233c0964a6588.mp3" }, { "id": "emo_Amusement-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-0", "key": "8b6e5f2a3451ea78f131113e647c8cc6b1b42d327ff7686b5ab45368bd93522c", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The door is still open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "5758e50f5228d95fd2b5427a79f5e5d91c28763a050dd9457dac06a5d508fff0", "generation_seconds_batch": 21.540829263045453, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3079540729522705, "target_z": 2.1093749935597295, "ce": 6.165581703186035, "genuineness": 3.4969046115875244, "identity": 0.4049857556819916, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/8b6e5f2a3451ea78f131113e647c8cc6b1b42d327ff7686b5ab45368bd93522c.mp3" }, { "id": "emo_Amusement-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-1", "key": "8b8b000c4f7d1e4bbd99830c80712cfae90f8a62a5350b241978dbf7811b0c93", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "65617d1cd6a5690b8e509cd567ec3e97baad0fc7ef6e68bdae2c0e3dbd67dc3c", "generation_seconds_batch": 22.59440247400198, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3621826171875, "target_z": 2.17187508801703, "ce": 6.332377910614014, "genuineness": 4.595211505889893, "identity": 0.4949556887149811, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/8b8b000c4f7d1e4bbd99830c80712cfae90f8a62a5350b241978dbf7811b0c93.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": "8bfaba62ee4014e01514054426adde2b2cdfd052dcb17594bec8b9d41bb81961", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "70270865c4129c308e308427f7a7b045b9a6fe2004a5dd722389d204c7fa56f7", "generation_seconds_batch": 27.29935980506707, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3420095443725586, "target_z": 0.9960936925742547, "ce": 6.062326908111572, "genuineness": 4.457139015197754, "identity": 0.6750603318214417, "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_Amusement/8bfaba62ee4014e01514054426adde2b2cdfd052dcb17594bec8b9d41bb81961.mp3" }, { "id": "emo_Amusement-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-1", "key": "8c60deff6db939dce0c3a7c6d0b1755a0fb631042ae2eb4eb751a8cb4d3a821b", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I found the little box.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It was beside the old window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d4c49118cf4f8840741d173d97879c659bb7a57a99cacc8a71fbbdebc895c9c0", "generation_seconds_batch": 21.575124165974557, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.850238561630249, "target_z": 2.734374838993238, "ce": 6.213237762451172, "genuineness": 4.017816066741943, "identity": 0.3436683416366577, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/8c60deff6db939dce0c3a7c6d0b1755a0fb631042ae2eb4eb751a8cb4d3a821b.mp3" }, { "id": "emo_Amusement-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-0", "key": "8c7c7cc500d41e2a34d0025d6e7ad0977a7f53b52efc18badb1fc2b5fc5e880e", "bucket": "emo_Amusement", "phase": "wording", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The door is still open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "1bcbd50b3609a615a7db7b46c8437d26eb469f5c4cad931a4239a3a907332a58", "generation_seconds_batch": 16.333980492083356, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3860702514648438, "target_z": 1.046875036494866, "ce": 6.117925643920898, "genuineness": 3.9550557136535645, "identity": 0.2371244877576828, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/8c7c7cc500d41e2a34d0025d6e7ad0977a7f53b52efc18badb1fc2b5fc5e880e.mp3" }, { "id": "emo_Amusement-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-0", "key": "8c98af4b4ebd69145815ce5103836b6ca353f863fc2d15f57a62c65001f4450a", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De deur staat nog open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "8f9c86626f63f7510ff34a359e3965155e76a1b9d35aa1bf7090eb642333dc21", "generation_seconds_batch": 18.676577002974227, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.375739574432373, "target_z": 2.1874999055426994, "ce": 6.117925643920898, "genuineness": 4.394378662109375, "identity": 0.4937852621078491, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/8c98af4b4ebd69145815ce5103836b6ca353f863fc2d15f57a62c65001f4450a.mp3" }, { "id": "emo_Amusement-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-1", "key": "8cb2f1b868a6c27191e458eaaebbba9cc6123f1073a0c3615cd58a9abba29ef5", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "0c7f09f72bf211cc329da10f8fc2c5107a8a93a66020b9c01323860a6caef061", "generation_seconds_batch": 22.549052483052947, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0978188514709473, "target_z": 1.8671875740631108, "ce": 5.871703147888184, "genuineness": 3.9048471450805664, "identity": 0.18604066967964172, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/8cb2f1b868a6c27191e458eaaebbba9cc6123f1073a0c3615cd58a9abba29ef5.mp3" }, { "id": "emo_Amusement-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-0", "key": "8ccbd7c9cecef52299c5fd01a39e38333e961fdafd89c2b57616c6ae85ac34b5", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "3ebce3e2ea6b3528c983a7386e02870b703f2e3025fc60b5ad3597cbba7d1161", "generation_seconds_batch": 23.956850653048605, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9554691314697266, "target_z": 1.7031250665494617, "ce": 6.23706579208374, "genuineness": 4.042920112609863, "identity": 0.3105030655860901, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/8ccbd7c9cecef52299c5fd01a39e38333e961fdafd89c2b57616c6ae85ac34b5.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": "8d4b9a0f257bf96a338f926f6083c0fd6051ea16bfb79eeff57da6a30781d439", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "81b870abb80c251165b05a128ab5ef8834281f25b3d7a3406a2ad8edfeef1c25", "generation_seconds_batch": 28.990558482939377, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1588258743286133, "target_z": 1.9375000772832458, "ce": 6.165581703186035, "genuineness": 3.9801597595214844, "identity": 0.6914515495300293, "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_Amusement/8d4b9a0f257bf96a338f926f6083c0fd6051ea16bfb79eeff57da6a30781d439.mp3" }, { "id": "emo_Amusement-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-0", "key": "8e1e980bb0d51f941a3340f5e970dc91731b091e4104a43442e2e053fe8238ac", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9b8b88e748c391d48efff3f66e6c2041b40acbffaf58d6866a8b4bce71723856", "generation_seconds_batch": 24.7968501530122, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.352177381515503, "target_z": 1.007812443110944, "ce": 6.324435234069824, "genuineness": 4.331617832183838, "identity": 0.6371309757232666, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/8e1e980bb0d51f941a3340f5e970dc91731b091e4104a43442e2e053fe8238ac.mp3" }, { "id": "emo_Amusement-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-0", "key": "8e667370fa47cf243aa970a2bc1d57f1c3ccfedb5ab9a16d5be956ff0286a277", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The door is still open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "9c96291958fa0c5087dc55d56b3fa0d5774ca808aeeaccd5c6f7815d651ac70c", "generation_seconds_batch": 21.540829263045453, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2808399200439453, "target_z": 2.0781250837235166, "ce": 6.165581703186035, "genuineness": 3.5973212718963623, "identity": 0.4132571816444397, "hypothesis": "A door is still open. I put your coats on the chair. Tell me when you are ready.", "wer": 0.1111111111111111, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/8e667370fa47cf243aa970a2bc1d57f1c3ccfedb5ab9a16d5be956ff0286a277.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": "8e7288cafeaa215add578add9598cdfbb6b982e6e7dc8958eba67c500ac9852d", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fccff997e79022deb480f2b78394b6443b62dee50e76f20b81c1d19b093d21d3", "generation_seconds_batch": 15.603356683044694, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.480970025062561, "target_z": 1.1562499957064862, "ce": 6.300607204437256, "genuineness": 4.268857479095459, "identity": 0.6472034454345703, "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_Amusement/8e7288cafeaa215add578add9598cdfbb6b982e6e7dc8958eba67c500ac9852d.mp3" }, { "id": "emo_Amusement-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-0", "key": "8ec87aecfa3c006d4d75464b8df751ccc4359c7854d3dc5024a240c852d606a3", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De deur staat nog open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "a35ccd2b5caec2946eb549fb53ff10dadeff8245e46de8a398d31c54f806107e", "generation_seconds_batch": 25.060368446982466, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.226611375808716, "target_z": 2.015624989266216, "ce": 5.919358730316162, "genuineness": 4.193545341491699, "identity": 0.7359095215797424, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/8ec87aecfa3c006d4d75464b8df751ccc4359c7854d3dc5024a240c852d606a3.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": "8ecec0185bc65c7d671c34f1457209fcee2bd9c35b61869cccf5addcd72a2311", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Escribí el número en el sobre.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "871fd9c64ec74849ec2d8c80b92eb6e7e9d26dc39f11b222969417b54b3b2c7a", "generation_seconds_batch": 17.294284036033787, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.118154525756836, "target_z": 1.890625075136489, "ce": 6.24500846862793, "genuineness": 4.425758361816406, "identity": 0.6429698467254639, "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_Amusement/8ecec0185bc65c7d671c34f1457209fcee2bd9c35b61869cccf5addcd72a2311.mp3" }, { "id": "emo_Amusement-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-0", "key": "8eeff4e279660a68e6bf4a6d0e5f1b1d241b8eeb065a2712bc9d95031e986499", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bdd14fb43f56bc31d7f05c23bf8847ab80fd3244cc5d4cff82dc53fa3a84d47e", "generation_seconds_batch": 23.329139773966745, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0029189586639404, "target_z": 1.7578124774590533, "ce": 6.173524379730225, "genuineness": 4.080576419830322, "identity": 0.535279393196106, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/8eeff4e279660a68e6bf4a6d0e5f1b1d241b8eeb065a2712bc9d95031e986499.mp3" }, { "id": "emo_Amusement-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-1", "key": "8f0b63602dd57d8ca9ebb15db470360575bad19e9af77dcbfe6f8da3187ee38f", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "3561fb8b21d774046774673e994e6b17102c6ae615e9d67bf6b84da9d74975df", "generation_seconds_batch": 24.086964361951686, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8773529529571533, "target_z": 2.765625023614325, "ce": 5.752562999725342, "genuineness": 3.948779582977295, "identity": 0.33941650390625, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/8f0b63602dd57d8ca9ebb15db470360575bad19e9af77dcbfe6f8da3187ee38f.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": "9008eb2612905a9c7d2e76c6475616cfa711fd4e3fbd17033be844b99767ddae", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fb9686ebc6a175188bb2de8c5185036a467d4170d716e2dd3a1ec72e3f1e2bed", "generation_seconds_batch": 16.35652410297189, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3725130558013916, "target_z": 1.0312499441843224, "ce": 6.0146708488464355, "genuineness": 4.482243061065674, "identity": 0.6162073612213135, "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_Amusement/9008eb2612905a9c7d2e76c6475616cfa711fd4e3fbd17033be844b99767ddae.mp3" }, { "id": "emo_Amusement-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-1", "key": "9030a085748ea76bf7ec6f99e76ab7fbbf507f740c0e86c4db439872c1d0db67", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2898319a108f76d6f204896b715271b83f2b83fe58960efbc341f857b7dc5e2d", "generation_seconds_batch": 23.51464685704559, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2808399200439453, "target_z": 2.0781250837235166, "ce": 6.340320587158203, "genuineness": 3.578493118286133, "identity": 0.5085115432739258, "hypothesis": "Ich hab die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/9030a085748ea76bf7ec6f99e76ab7fbbf507f740c0e86c4db439872c1d0db67.mp3" }, { "id": "emo_Amusement-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-1", "key": "905a808941630a19325e74d8983092ba75eb4529371ae6f10262e2e504db0d83", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "8f03040c9f725754412af26f1b5d5e3329ec22c7d57a5dfe500235fb7961902e", "generation_seconds_batch": 25.11776234197896, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.084261655807495, "target_z": 1.8515624817525669, "ce": 6.260893821716309, "genuineness": 4.2751336097717285, "identity": 0.6618163585662842, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/905a808941630a19325e74d8983092ba75eb4529371ae6f10262e2e504db0d83.mp3" }, { "id": "emo_Amusement-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-1", "key": "9069e145dfdaf9dc7d6ea0132aa231d53179c59e5b7932303df8b34e04f8b959", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "814bd80bced3ab46e549e5ec1917947aead7f9ca5ef376672080e6de5f67e434", "generation_seconds_batch": 18.701121035963297, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2098276615142822, "target_z": 0.843749935597295, "ce": 6.252951145172119, "genuineness": 4.6956281661987305, "identity": 0.7141772508621216, "hypothesis": "J'ai trouvé la 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_Amusement/9069e145dfdaf9dc7d6ea0132aa231d53179c59e5b7932303df8b34e04f8b959.mp3" }, { "id": "emo_Amusement-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-1", "key": "90c85a36fb5b85928f87a1cbea896f3f935bdda09b75dc36470f916c16446418", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "36756d191b0e3bd5ff205943f18370cd7f8398b6af140093ae0e42bbf26dd012", "generation_seconds_batch": 21.881724565988407, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8539534211158752, "target_z": 0.4335937355093914, "ce": 6.173524379730225, "genuineness": 4.482243061065674, "identity": 0.7054986953735352, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/90c85a36fb5b85928f87a1cbea896f3f935bdda09b75dc36470f916c16446418.mp3" }, { "id": "emo_Amusement-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-0", "key": "90e694c515491849ba0b12b6f66f78ef1e56336ea97843542f7e25c9a882c474", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "3467ac848d605750c68ead00ab7c03c0d756e6b3ad0c983b2a7172313c06290c", "generation_seconds_batch": 26.3998201219365, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2130541801452637, "target_z": 1.999999896955672, "ce": 5.728734970092773, "genuineness": 3.540836811065674, "identity": 0.2492220401763916, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/90e694c515491849ba0b12b6f66f78ef1e56336ea97843542f7e25c9a882c474.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": "934a7a94bcb4203d822cbd036d98742329353482117771cc5b6453362f3070df", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Someone moved the little blue chair.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dd77cf29ca307e7559dbb288795c11fb8926349f0cb5d82515b7ea818e4357c3", "generation_seconds_batch": 18.262527006911114, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.243720531463623, "target_z": 0.8828125289812172, "ce": 6.38003396987915, "genuineness": 4.15588903427124, "identity": 0.41983556747436523, "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_Amusement/934a7a94bcb4203d822cbd036d98742329353482117771cc5b6453362f3070df.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": "9361056c6b4db86bf1b1d247e5a681d800f2d9845c4779fe61bed269ab76cdb2", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0d3fcf5d3e061d042feb2ce99e1ab9bf5d3172afcb04de2a353580b1bf3e84cc", "generation_seconds_batch": 20.23383317294065, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.104597330093384, "target_z": 1.8749999828259454, "ce": 6.443574905395508, "genuineness": 4.344170093536377, "identity": 0.5737109184265137, "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_Amusement/9361056c6b4db86bf1b1d247e5a681d800f2d9845c4779fe61bed269ab76cdb2.mp3" }, { "id": "emo_Amusement-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-1", "key": "937c63929340607a951c006b050282b96b4902c8ece5cb702580eb4d116c8d98", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "35ef70fec9664c2f61e2066428d7671a8eda81078a206d6438861a77a9c27c36", "generation_seconds_batch": 24.14048035198357, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9993669986724854, "target_z": 2.9062500300545957, "ce": 6.252951145172119, "genuineness": 3.8420867919921875, "identity": 0.37444689869880676, "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_Amusement/937c63929340607a951c006b050282b96b4902c8ece5cb702580eb4d116c8d98.mp3" }, { "id": "emo_Amusement-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-1", "key": "9391939c0e611f35eea5d2c13ee08e95593b0840b558822d90c1bea8d05c2bff", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I found the little box.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It was beside the old window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "b5d1724f22a0e003df2abbb9029c9972f46c4dbb828fbc88bd481b3296a2acc6", "generation_seconds_batch": 23.903421266004443, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8876835107803345, "target_z": 1.6250000171740546, "ce": 6.316492557525635, "genuineness": 4.519899368286133, "identity": 0.4922054708003998, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/9391939c0e611f35eea5d2c13ee08e95593b0840b558822d90c1bea8d05c2bff.mp3" }, { "id": "emo_Amusement-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-0", "key": "93e828bc1975d02ef43408156f735c667aff2f97e576ead986bee1483c0270de", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The door is still open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "57d4d67b73d074baf947230bbe06f42b9e8b0eb295ce2f48f0e4f137694106d5", "generation_seconds_batch": 18.750275145983323, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6504340171813965, "target_z": 1.3515625504487856, "ce": 6.197352409362793, "genuineness": 4.055472373962402, "identity": 0.1836874634027481, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/93e828bc1975d02ef43408156f735c667aff2f97e576ead986bee1483c0270de.mp3" }, { "id": "emo_Amusement-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-0", "key": "9445b3cc063c839b0d541efd1325b33c1aaca0efcfce3d12ead81768360435e5", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The door is still open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "0523081df3e0fa7d330322937d701957c86d56b753b9c39420e27344a3ea6bac", "generation_seconds_batch": 23.288646325003356, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4570822715759277, "target_z": 2.281249909836213, "ce": 6.260893821716309, "genuineness": 3.760498285293579, "identity": 0.3951849937438965, "hypothesis": "The door's still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.1111111111111111, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/9445b3cc063c839b0d541efd1325b33c1aaca0efcfce3d12ead81768360435e5.mp3" }, { "id": "emo_Amusement-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-1", "key": "94814d7cd597b953a95661eed29f24efa343f66a7e735c0d120421967884801e", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I found the little box.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It was beside the old window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "d46a78366dfc3b1006be7bc527545c9947454e1b1a2290b5de5ada79867711f6", "generation_seconds_batch": 20.536168513004668, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.47063946723938, "target_z": 2.296875002146757, "ce": 6.205295085906982, "genuineness": 3.8671910762786865, "identity": 0.31381213665008545, "hypothesis": "I found a little box. It was beside the old window. We can look inside together.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/94814d7cd597b953a95661eed29f24efa343f66a7e735c0d120421967884801e.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": "94a5db322269682e59c2db6de16dbc6f6df8182038f1a82f4505558a2c7771a7", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [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": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "8f8b5a0a07fcd7f37492c2fc5dab7bab3992d9359767052246ce10830ffedf89", "generation_seconds_batch": 17.609773666015826, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.497753620147705, "target_z": 2.32812491198297, "ce": 6.308549880981445, "genuineness": 4.394378662109375, "identity": 0.7317244410514832, "hypothesis": "Las llaves están en la mesa de la cocina. Miré en el cajón y luego junto a la ventana. Llévatelas cuando te vayas.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/94a5db322269682e59c2db6de16dbc6f6df8182038f1a82f4505558a2c7771a7.mp3" }, { "id": "emo_Amusement-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-1", "key": "94c857bda8af032a8eac7818061d96e443f0ec7a30e7026a89f7bef8f161d5a3", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "250e5b07b06b6fd2b5ef870bd0901b98f13048be6c73e620dc53f76eba2d9d11", "generation_seconds_batch": 17.67168299900368, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5013056993484497, "target_z": 1.1796874967798647, "ce": 6.475345611572266, "genuineness": 4.256305694580078, "identity": 0.5446634292602539, "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_Amusement/94c857bda8af032a8eac7818061d96e443f0ec7a30e7026a89f7bef8f161d5a3.mp3" }, { "id": "emo_Amusement-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-0", "key": "953fa7887f742ee101825788d0486740c02304fd7577cd69f47ba13887765b4f", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "c2ad7c0434e45aff3ca7e7080130a1881dfda88a1074a0c9d98809ed5b76d6d4", "generation_seconds_batch": 20.652963318047114, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9657996296882629, "target_z": 0.5624999914129727, "ce": 6.205295085906982, "genuineness": 4.494794845581055, "identity": 0.6669355630874634, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/953fa7887f742ee101825788d0486740c02304fd7577cd69f47ba13887765b4f.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": "9568a9ffd75450c9ece306c0ef1997f5754fba48233b480ddff2e6134c060022", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "17a10c5da38f98545bf829a91c610f83550f888985dcdaa8580e78510784a037", "generation_seconds_batch": 18.680346278939396, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3453989028930664, "target_z": 1.0000000343481092, "ce": 6.300607204437256, "genuineness": 4.469690799713135, "identity": 0.6400982737541199, "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_Amusement/9568a9ffd75450c9ece306c0ef1997f5754fba48233b480ddff2e6134c060022.mp3" }, { "id": "emo_Amusement-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-1", "key": "95dc62422a9ee3b57cad35ee532e03a1953f534d9ab4de3c564fc99e0c8eb6c6", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "b798b35cdf1f3b09431410b42ad2399153eb557d70b51b938b139b5610f08169", "generation_seconds_batch": 24.537725646048784, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5248677730560303, "target_z": 2.3593748218191832, "ce": 6.038498878479004, "genuineness": 4.055472373962402, "identity": 0.6173633337020874, "hypothesis": "J'ai trouvé la 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_Amusement/95dc62422a9ee3b57cad35ee532e03a1953f534d9ab4de3c564fc99e0c8eb6c6.mp3" }, { "id": "emo_Amusement-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-0", "key": "96165dcf1e25455f69011eaaccf7da1f69012f831e631d8e74059514f444e383", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9ea3c6533a3f1d5533b7d452f4113bc19599d8c85dce941e6e64f7c1b5d294c8", "generation_seconds_batch": 25.535106010036543, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1113758087158203, "target_z": 1.88281239158878, "ce": 6.348263263702393, "genuineness": 4.331617832183838, "identity": 0.6580836772918701, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/96165dcf1e25455f69011eaaccf7da1f69012f831e631d8e74059514f444e383.mp3" }, { "id": "emo_Amusement-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-0", "key": "9654d6e67747bb21e7b960f13a1d12eb2702d75a3f185a36d8d296642687f30a", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "a92e26702788cd03e85ab168fc7910d7cafe3d70ebae4940a9fef9eedc8ba1c7", "generation_seconds_batch": 22.32041623000987, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6775482892990112, "target_z": 1.382812597677436, "ce": 6.229123115539551, "genuineness": 4.281409740447998, "identity": 0.3023948669433594, "hypothesis": "Die Tür ist noch offen, ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/9654d6e67747bb21e7b960f13a1d12eb2702d75a3f185a36d8d296642687f30a.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": "965dedef700496b9099a7911c7de304fa1ab84c79e352f07d1a94b276f8da02d", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f877c8e3626acd436b70ab8cdc2cdcc39244d3ae28be558b5912a30d96527aa9", "generation_seconds_batch": 17.609773666015826, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9147977828979492, "target_z": 1.656250064402705, "ce": 6.205295085906982, "genuineness": 4.432034492492676, "identity": 0.4846515953540802, "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_Amusement/965dedef700496b9099a7911c7de304fa1ab84c79e352f07d1a94b276f8da02d.mp3" }, { "id": "emo_Amusement-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-1", "key": "969a239cfdba00ee1a64398c6c37c5b8a47bc930ede364f2d3ee43504d1f9147", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "56f16af50efcd11b089d37f55eb659627a135f09b31bf885f7cb481163424632", "generation_seconds_batch": 20.339048321940936, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.070704460144043, "target_z": 1.8359373894420232, "ce": 6.062326908111572, "genuineness": 4.268857479095459, "identity": 0.2656407654285431, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/969a239cfdba00ee1a64398c6c37c5b8a47bc930ede364f2d3ee43504d1f9147.mp3" }, { "id": "emo_Amusement-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-0", "key": "973ba1c1c3954c8371a8a04037cf115be160e33975ed90e1b783d3823c240634", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De deur staat nog open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "24e7154b43f04650adcc0ccaf5a7f6d7d3184b9c84e8ab1cfc27695a0afa87e2", "generation_seconds_batch": 24.81203827599529, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.023254632949829, "target_z": 1.7812499785324316, "ce": 5.95112943649292, "genuineness": 4.093128204345703, "identity": 0.14380180835723877, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/973ba1c1c3954c8371a8a04037cf115be160e33975ed90e1b783d3823c240634.mp3" }, { "id": "emo_Amusement-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-0", "key": "97506e44ddf97be1f52f33ef4cc0d3f194a5439eb083a8e6c268fa4d11246f91", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "cf3335800f272fb96ec6fc7390ef9cd4b99a174ba30b645216dec2dd1fdb5922", "generation_seconds_batch": 22.18319084099494, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2840662002563477, "target_z": 3.234374770297019, "ce": 6.308549880981445, "genuineness": 4.093128204345703, "identity": 0.5209319591522217, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/97506e44ddf97be1f52f33ef4cc0d3f194a5439eb083a8e6c268fa4d11246f91.mp3" }, { "id": "emo_Amusement-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-1", "key": "975eae62ed95de99b6c2c171ab141c76fa5b8b6d702486929332642853f2c1d6", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "432a609c98be07b7a9db7d6884c173d94966fe2d347f812d119c425d4ac61e74", "generation_seconds_batch": 20.328051723889075, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.958695650100708, "target_z": 2.8593750279078387, "ce": 5.990842819213867, "genuineness": 4.331617832183838, "identity": 0.20631343126296997, "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_Amusement/975eae62ed95de99b6c2c171ab141c76fa5b8b6d702486929332642853f2c1d6.mp3" }, { "id": "emo_Amusement-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-1", "key": "979b87fef388cf43fda05cafaf2b7ed791c84c904d66a56c44c10b247b9cc8f6", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "eced94bf455a8e59bf093fe053c0c091a45f1543e8282612dbc7a2253caa1144", "generation_seconds_batch": 25.56944321701303, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5113108158111572, "target_z": 2.3437500042935135, "ce": 5.824047088623047, "genuineness": 4.507347106933594, "identity": 0.7248957753181458, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/979b87fef388cf43fda05cafaf2b7ed791c84c904d66a56c44c10b247b9cc8f6.mp3" }, { "id": "emo_Amusement-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-0", "key": "97a49eb1cd000edc242e3c2dfe8467f15596d3869840d8990b40f9e46e94f41b", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De deur staat nog open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "a3e12122fe2e7b48e512c8d719a22ab50566cf35885cfee6f53d91922807a60e", "generation_seconds_batch": 24.230325113981962, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4570822715759277, "target_z": 2.281249909836213, "ce": 6.062326908111572, "genuineness": 4.193545341491699, "identity": 0.6595252156257629, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/97a49eb1cd000edc242e3c2dfe8467f15596d3869840d8990b40f9e46e94f41b.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": "97c4f62954e720e8d68a3dd16a2e15cb49b56cfb20a17ec4de8f84cbbe98409f", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "72ddb86f95217231c5dbd9a8f55fb5867bde1599c067def8695927a7b8f23e14", "generation_seconds_batch": 18.439058294985443, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3013381958007812, "target_z": 0.949218690427498, "ce": 6.419747352600098, "genuineness": 4.507347106933594, "identity": 0.57386314868927, "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_Amusement/97c4f62954e720e8d68a3dd16a2e15cb49b56cfb20a17ec4de8f84cbbe98409f.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": "97ce12c5fc77f77c9f274f6336f9ba26a072f5570ac5be58725f878989ee100a", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a8579b234417875dc9f4755ac1539caf2ccd21883ba200c8c3bfb5471bb8239b", "generation_seconds_batch": 18.439058294985443, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1994972229003906, "target_z": 1.9843750794300028, "ce": 6.348263263702393, "genuineness": 4.494794845581055, "identity": 0.651697039604187, "hypothesis": "Die Schlüsse liegen auf dem Küchentisch. Ich suchte in der Schublade dann neben dem Fenster. Nimm sie mit, wenn du gehst.", "wer": 0.047619047619047616, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/97ce12c5fc77f77c9f274f6336f9ba26a072f5570ac5be58725f878989ee100a.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": "97e9374be538f8f79796dec20289d98c7ac508d3d78905e2fd35e86362b1e12a", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9da35042ed56682c87eb08f5c7c57aca662db85bbeae690c523ae7aeab65540d", "generation_seconds_batch": 19.667723782011308, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1352635622024536, "target_z": 0.7578124774590532, "ce": 6.2767791748046875, "genuineness": 4.469690799713135, "identity": 0.5544026494026184, "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_Amusement/97e9374be538f8f79796dec20289d98c7ac508d3d78905e2fd35e86362b1e12a.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": "97ed0d5bdedb8ea25c5eb6a32fa23982314f5584da85760983dc7502f26f618b", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9e6658c88253315a2ed6c367f042e0c91b3f04cc3d5010229853378d6df7e955", "generation_seconds_batch": 20.12339791096747, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0368118286132812, "target_z": 1.7968750708429755, "ce": 6.1020402908325195, "genuineness": 4.406930446624756, "identity": 0.44613683223724365, "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_Amusement/97ed0d5bdedb8ea25c5eb6a32fa23982314f5584da85760983dc7502f26f618b.mp3" }, { "id": "emo_Amusement-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-1", "key": "97fa2a809b8793b55145ad551a52168caa4bc1f5b97828da0a1dd9d456e24ad2", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I found the little box.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It was beside the old window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "0e4541a41300aab727a436107ab8760b0920c87ced99b2e9d0ea67f5ae7d71f4", "generation_seconds_batch": 26.46711249393411, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0774831771850586, "target_z": 1.8437500729897323, "ce": 6.372091293334961, "genuineness": 4.231201171875, "identity": 0.4330880641937256, "hypothesis": "I found the little box. It was beside the old window. We can look inside together,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/97fa2a809b8793b55145ad551a52168caa4bc1f5b97828da0a1dd9d456e24ad2.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": "98565c84f1a297948d390c3988349ae9e23a89b553842136aee59324d43f6773", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "595865fdcd5b9e6d9c66192d2b2e0f2d1cdf1a32429f8d444c179de718698e36", "generation_seconds_batch": 29.769972286070697, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5148628950119019, "target_z": 1.1953125890904084, "ce": 6.41180419921875, "genuineness": 4.519899368286133, "identity": 0.38367587327957153, "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_Amusement/98565c84f1a297948d390c3988349ae9e23a89b553842136aee59324d43f6773.mp3" }, { "id": "emo_Amusement-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-1", "key": "986897605dbc08edbddb5104d50557c5f9c21a332850c949b6ffa1f992b1b852", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "454f1e46227bfd90583b46095bfe35257ad7472672211bbda71300c6e7563fb1", "generation_seconds_batch": 19.25713780906517, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6468818187713623, "target_z": 2.4999998282594533, "ce": 6.109982967376709, "genuineness": 4.300237655639648, "identity": 0.553184449672699, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/986897605dbc08edbddb5104d50557c5f9c21a332850c949b6ffa1f992b1b852.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": "986f634f576f35171da90d4926a8302638e365d7d0cb875f1f172525b11b9ddc", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "fe893bc6ab66035e7c5e1c345520c4a939e1d2f2a2907510cd9f6c95018b34cd", "generation_seconds_batch": 15.08638767094817, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7927837371826172, "target_z": 1.5156250579624344, "ce": 6.38797664642334, "genuineness": 4.369274139404297, "identity": 0.6776013970375061, "hypothesis": "Las llaves están en la mesa de la cocina. Miren el cajón y luego, junto a la ventana, llévatelas cuando te vayas.", "wer": 0.08695652173913043, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/986f634f576f35171da90d4926a8302638e365d7d0cb875f1f172525b11b9ddc.mp3" }, { "id": "emo_Amusement-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-1", "key": "98bd0ad5f94d2007408bbaa28315cfa9ff6aa474024648ac369629c143840a00", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "d21273654acb1aac336295eff23bb635286a0ab680c87b97f64419ebc790cac9", "generation_seconds_batch": 21.96719250897877, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0776458978652954, "target_z": 0.6914063160127726, "ce": 6.229123115539551, "genuineness": 4.532451152801514, "identity": 0.6351543664932251, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/98bd0ad5f94d2007408bbaa28315cfa9ff6aa474024648ac369629c143840a00.mp3" }, { "id": "emo_Amusement-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-0", "key": "992cdd94a4866ae2ad490f2c7ba5380b9b1336d2d6bbb8a4df96623087fea988", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "ee86a05771da2efe5a6bcf1afbe62b076aae3257be9fcae87be95624d47d9b80", "generation_seconds_batch": 20.840472667943686, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2976233959198, "target_z": 3.249999862607563, "ce": 6.157639026641846, "genuineness": 4.65797233581543, "identity": 0.6939774751663208, "hypothesis": "La porte est encore ouverte j'ai posé ton manteau sur la chaise dis-moi quand tu es prêt", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/992cdd94a4866ae2ad490f2c7ba5380b9b1336d2d6bbb8a4df96623087fea988.mp3" }, { "id": "emo_Amusement-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-1", "key": "99367087f9736b64a392e5b0d2c69776b12592822d19de88b207482dd506b1f9", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "16f636f4957d5467988aad02c670643ecb3b878d1e4de46c32ea2e54a461bcd7", "generation_seconds_batch": 24.537725646048784, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4028539657592773, "target_z": 2.218750090163787, "ce": 6.252951145172119, "genuineness": 4.262581825256348, "identity": 0.6226100921630859, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/99367087f9736b64a392e5b0d2c69776b12592822d19de88b207482dd506b1f9.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": "993c80794600fc790b0aab9ef68de715f4bec8369f02215caae91d3bb811c8ae", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cdef14f9b5705c9671056855432f1864c8a854e9ab344961919434a780b01eaf", "generation_seconds_batch": 15.089088803972118, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0878137350082397, "target_z": 0.7031250665494617, "ce": 6.1894097328186035, "genuineness": 4.344170093536377, "identity": 0.7729908227920532, "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_Amusement/993c80794600fc790b0aab9ef68de715f4bec8369f02215caae91d3bb811c8ae.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_Amusement", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": "580ae310c32ce152004d987489123cc69f991733c98cb5b6e72ec80dc64349fd", "generation_seconds_batch": 17.359042542986572, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7827786207199097, "target_z": 0.35156255044878554, "ce": 6.316492557525635, "genuineness": 4.607763767242432, "identity": 0.6163089871406555, "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_Amusement/99bf1b7d3eed7b885fdae888ab00b4960791c3971d259b46f771306d2801e39b.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": "9a2aeaa5c8a6a3bc5935ac467e09fbccff126a84c7cce350ff48ffb97df7ed57", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b48c2487e10b94f42f05f00397ee58a7e23d763bdfc45d63bb59ad6f25b6e4e1", "generation_seconds_batch": 17.584241957054473, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.606210470199585, "target_z": 2.4531248261126968, "ce": 6.197352409362793, "genuineness": 4.362998008728027, "identity": 0.17302274703979492, "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_Amusement/9a2aeaa5c8a6a3bc5935ac467e09fbccff126a84c7cce350ff48ffb97df7ed57.mp3" }, { "id": "emo_Amusement-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-0", "key": "9a61eb7c3726972d657f61af13282639e6077f0c0d29744427f0e679813521dc", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The door is still open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "b7a0cf70e4d9db39b2c5327766902670076c8c20d828a9b8b7eaca416a45d24d", "generation_seconds_batch": 24.34233834699262, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.389296770095825, "target_z": 2.203124997853243, "ce": 6.300607204437256, "genuineness": 3.6789097785949707, "identity": 0.2434944212436676, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/9a61eb7c3726972d657f61af13282639e6077f0c0d29744427f0e679813521dc.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": "9ac61ec86122fec06b59b10cf706494b7f8ca784ef3033bd8c898cf1c03e8842", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e5137dbab6968b00daaacfa795988fd975191286f2da90e8e2fd2e6b93a239fe", "generation_seconds_batch": 16.35652410297189, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4064059257507324, "target_z": 1.0703125375682445, "ce": 6.141753673553467, "genuineness": 4.331617832183838, "identity": 0.5861191749572754, "hypothesis": "J'écris le numéro sur l'enveloppe, lis le bien et vérifie les deux derniers chiffres. Appelle-moi quand tu auras un moment.", "wer": 0.09090909090909091, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/9ac61ec86122fec06b59b10cf706494b7f8ca784ef3033bd8c898cf1c03e8842.mp3" }, { "id": "emo_Amusement-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-0", "key": "9b3c34dc8a31a4e6106d352e8f7b977b3a3751f158a46467f9cda9845882df02", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "0593225d0c7a96491ce56eecb671bb18b717a1e133f33f06e25f7fd26f750425", "generation_seconds_batch": 25.272795883007348, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7453337907791138, "target_z": 1.4609375096604058, "ce": 6.109982967376709, "genuineness": 4.250029563903809, "identity": 0.5095469951629639, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/9b3c34dc8a31a4e6106d352e8f7b977b3a3751f158a46467f9cda9845882df02.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_Amusement", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": "ad382a1068b50660983d4a1a03ae994855e87dd91dea293e95dff7939cfb86c5", "generation_seconds_batch": 17.46489887998905, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9522424936294556, "target_z": 0.5468749677986475, "ce": 6.316492557525635, "genuineness": 4.545003414154053, "identity": 0.7295942306518555, "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_Amusement/9c09e940c5dab53287ffae2d1a8fa5296f41b2df71714656aaa2bb8830bf5162.mp3" }, { "id": "emo_Amusement-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-0", "key": "9c8f1e80474fa5f65f844521e6f4dd5d6fe49fcf26239c0f236cd46271254f4d", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "253dc268423462dd64cdb0195f9c7255fea09a6f475f6ce48481b6c7f2c8dcde", "generation_seconds_batch": 23.9782854730729, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0335851907730103, "target_z": 0.6406249720921612, "ce": 6.0305562019348145, "genuineness": 3.625563621520996, "identity": 0.37752968072891235, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime, ¿cuándo estás listo?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/9c8f1e80474fa5f65f844521e6f4dd5d6fe49fcf26239c0f236cd46271254f4d.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_Amusement", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": "bcd8cbdad7a1a83873aeb224b521bb4f5a2db89cf8dbdc524c0a2ff17d446181", "generation_seconds_batch": 17.238110812031664, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6895734071731567, "target_z": 0.2441406247316554, "ce": 6.205295085906982, "genuineness": 4.394378662109375, "identity": 0.6889075040817261, "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_Amusement/9c969db20a6db380e08592f6aed9c9189b3db634d677ebe8f573f593ebdfd2d3.mp3" }, { "id": "emo_Amusement-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-0", "key": "9cb90ac2f6358b082693297d74ded03a95a58bdd1789f24e9a6553d44c89be48", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De deur staat nog open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "bdc4b79f774166eeaf98754520e9168502d8f4380d6dfbe85c45f98135cc75d2", "generation_seconds_batch": 23.873053429997526, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3621826171875, "target_z": 2.17187508801703, "ce": 6.0305562019348145, "genuineness": 4.369274139404297, "identity": 0.5671903491020203, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/9cb90ac2f6358b082693297d74ded03a95a58bdd1789f24e9a6553d44c89be48.mp3" }, { "id": "emo_Amusement-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-0", "key": "9cd483d515ad2ce57a90be261b66c77adf558e3f0df97dde14ca03a43dd38662", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "1fc5dd971521dd5da64184a2b8e7c619ad0108979be6da3e0d12940e12b752ed", "generation_seconds_batch": 25.54260477796197, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3182846307754517, "target_z": 0.968749987119459, "ce": 6.332377910614014, "genuineness": 4.381826400756836, "identity": 0.46096494793891907, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/9cd483d515ad2ce57a90be261b66c77adf558e3f0df97dde14ca03a43dd38662.mp3" }, { "id": "emo_Amusement-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-1", "key": "9d509b2a6e87266d9b9f24314aab16d4ed130b77d0f0772e75218162396e8861", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "e2141f8c24ec2130071cdad6a95f4938adee3fccf68802b66e5b0e906e5d01c8", "generation_seconds_batch": 24.997748160967603, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5758699178695679, "target_z": 1.2656250923105437, "ce": 6.09409761428833, "genuineness": 4.20609712600708, "identity": 0.5760791301727295, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/9d509b2a6e87266d9b9f24314aab16d4ed130b77d0f0772e75218162396e8861.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": "9dd4770f72a81361ee3554f9d3745e94dacd3967b10690c49d8c44750caa3524", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "72656398563e9e598cc7ece0e9279d4a032300967c0393ac271a59ae81f1dbc7", "generation_seconds_batch": 22.141370580997318, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5655391216278076, "target_z": 2.40624982396594, "ce": 6.1894097328186035, "genuineness": 4.042920112609863, "identity": 0.7427724599838257, "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_Amusement/9dd4770f72a81361ee3554f9d3745e94dacd3967b10690c49d8c44750caa3524.mp3" }, { "id": "emo_Amusement-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-0", "key": "9e05619db07499c640885e30033b1d5ba4383564633ecc9055dfc5589f75fbfd", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "d6de1056c35a6bdb82eb9d642d06c9f3c4c1bb47c84464fb2c2624ef10ad1d19", "generation_seconds_batch": 16.828103912994266, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.070704460144043, "target_z": 1.8359373894420232, "ce": 5.8875885009765625, "genuineness": 3.798154592514038, "identity": 0.47299957275390625, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/9e05619db07499c640885e30033b1d5ba4383564633ecc9055dfc5589f75fbfd.mp3" }, { "id": "emo_Amusement-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-1", "key": "9e432df8f55416f76db7d099d3c40af551215e8552fbd813866cfde8fc28fbc9", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "69e4a4ee46ab75a22aa6d7de280f7713ed653152a7e910f3594e6d7a9d1565aa", "generation_seconds_batch": 16.045714076957665, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5384249687194824, "target_z": 2.374999914129727, "ce": 6.1894097328186035, "genuineness": 4.557555198669434, "identity": 0.7004294991493225, "hypothesis": "J'ai trouvé la 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_Amusement/9e432df8f55416f76db7d099d3c40af551215e8552fbd813866cfde8fc28fbc9.mp3" }, { "id": "emo_Amusement-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-1", "key": "9e612ab91d8c7c122cae798d6d3ccb778452ac1338a20179ed15621bdaeada78", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "df773fe95ed1f9e220111c03090ff65244a99786422dfdb1969d31e03581d58c", "generation_seconds_batch": 25.962647582986392, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1962705850601196, "target_z": 0.8281249806791885, "ce": 6.141753673553467, "genuineness": 4.15588903427124, "identity": 0.667495608329773, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/9e612ab91d8c7c122cae798d6d3ccb778452ac1338a20179ed15621bdaeada78.mp3" }, { "id": "emo_Amusement-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-0", "key": "9ecb3ec1b0184d0a15efe9ea6360091443a72856124e005e42c44ed82d6a984d", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "b0eee03b3345133a328428a17a7232c1020a8baff4c6e37c1f921b9e834de1cd", "generation_seconds_batch": 23.113799753948115, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7995622158050537, "target_z": 1.523437466725269, "ce": 6.181467056274414, "genuineness": 4.319066047668457, "identity": 0.5651019811630249, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/9ecb3ec1b0184d0a15efe9ea6360091443a72856124e005e42c44ed82d6a984d.mp3" }, { "id": "emo_Amusement-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-1", "key": "9fadf14c95f066d72b00b0cbdd20b4a57bb168bb34a1c4704526a4f1c874056f", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "b16d0b3a82a9756991815e90be610dc58cfef0052352b57171eae687d1270f45", "generation_seconds_batch": 21.367572588962503, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.352177381515503, "target_z": 1.007812443110944, "ce": 6.419747352600098, "genuineness": 4.300237655639648, "identity": 0.43018972873687744, "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_Amusement/9fadf14c95f066d72b00b0cbdd20b4a57bb168bb34a1c4704526a4f1c874056f.mp3" }, { "id": "emo_Amusement-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-0", "key": "9fdfb5ed189bf910f18523c5218ea0ab07ed1f1c0aaec7a67ec65905c084045e", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The door is still open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b3f1a0655a0daa59d534e8a4f43bdebad276fa83ab6223ff004cb7d93ba5f563", "generation_seconds_batch": 21.74795415601693, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0300331115722656, "target_z": 1.7890623872952665, "ce": 6.0305562019348145, "genuineness": 3.7040140628814697, "identity": 0.39999353885650635, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/9fdfb5ed189bf910f18523c5218ea0ab07ed1f1c0aaec7a67ec65905c084045e.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": "a02883b7781a64c4f1f9e941ef24d099afe5e3794f4a6f1d59aba6bff1592837", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "316060173af86f10eadfc70c224c1abf8843f7afa7b50365d85b4d68718ccb19", "generation_seconds_batch": 20.252199482056312, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.230163335800171, "target_z": 0.8671874366706734, "ce": 6.300607204437256, "genuineness": 3.9048471450805664, "identity": 0.5626422166824341, "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_Amusement/a02883b7781a64c4f1f9e941ef24d099afe5e3794f4a6f1d59aba6bff1592837.mp3" }, { "id": "emo_Amusement-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-0", "key": "a05c2aa79f5353c7de240690ac7c1a7e2c685c01ac3e3419ded469d093afcfc8", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "39a28b6b1b7683cd3280d1cd8825d46d47de81231577491f1bb1cb4da9ed7db4", "generation_seconds_batch": 23.176861499086954, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0098602771759033, "target_z": 0.6132812666373655, "ce": 5.967014789581299, "genuineness": 3.8797430992126465, "identity": 0.4945674538612366, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/a05c2aa79f5353c7de240690ac7c1a7e2c685c01ac3e3419ded469d093afcfc8.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": "a0da1b4349ea235cdd16d5442aa9027fc35f4d02ba2e9f3c8890a7c6f5516c46", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "65da7c2d8d7068a832a835426ed710fd7daafdb223d6e31ff78bbc57bf78183d", "generation_seconds_batch": 28.990558482939377, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3621826171875, "target_z": 2.17187508801703, "ce": 6.340320587158203, "genuineness": 4.118232727050781, "identity": 0.6249993443489075, "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_Amusement/a0da1b4349ea235cdd16d5442aa9027fc35f4d02ba2e9f3c8890a7c6f5516c46.mp3" }, { "id": "emo_Amusement-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-0", "key": "a1046564666ea54e61e5d262777d1b51d65e1d378de9672dfc59ac0394c764ba", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e5d535d1aa1384a8ae706a1cfe3079ef8213f8223871c9f319ff2f1a529e6950", "generation_seconds_batch": 21.654846042045392, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1994972229003906, "target_z": 1.9843750794300028, "ce": 6.23706579208374, "genuineness": 4.011539936065674, "identity": 0.4655756652355194, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/a1046564666ea54e61e5d262777d1b51d65e1d378de9672dfc59ac0394c764ba.mp3" }, { "id": "emo_Amusement-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-0", "key": "a1341b8bebced462d63cf43c2dbfd67e5fcdc625a6414b425552b0add78337d4", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "685d54a718d715e16911c14a8d185721479637519ef586fa2d52023a0bc931e1", "generation_seconds_batch": 19.185466383001767, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.358955979347229, "target_z": 1.015624989266216, "ce": 6.070269584655762, "genuineness": 4.406930446624756, "identity": 0.6461420059204102, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/a1341b8bebced462d63cf43c2dbfd67e5fcdc625a6414b425552b0add78337d4.mp3" }, { "id": "emo_Amusement-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-0", "key": "a17a77e2739c736b0b60c3cf5a032bce1a859082a1e8bcc72086770ada00a0a7", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "4ce991843193481e21a18982274f407025fba19a465bf7a4f8684ba721a20a15", "generation_seconds_batch": 16.88433630100917, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1657670736312866, "target_z": 0.7929687290691209, "ce": 6.332377910614014, "genuineness": 4.6203155517578125, "identity": 0.39916491508483887, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/a17a77e2739c736b0b60c3cf5a032bce1a859082a1e8bcc72086770ada00a0a7.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": "a17e7b304f2c1b613a1b07a9bbd59e8d6647a4e3f09ba129c6aeec6c80545dc9", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "dcf22e2ef13f3403f46e3d64bd0272a95b3199be0e07d94cc7de71b93ce63de9", "generation_seconds_batch": 29.783178596990183, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7724480628967285, "target_z": 1.492187556889056, "ce": 6.284721851348877, "genuineness": 4.15588903427124, "identity": 0.6072937846183777, "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_Amusement/a17e7b304f2c1b613a1b07a9bbd59e8d6647a4e3f09ba129c6aeec6c80545dc9.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": "a1ad54b397cfc1ea57f31207ad50ba9777acc058eafe37d28d2fe034b33fd003", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I wrote the number on the envelope.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d2e4a30cf27e0f3b36189af1ad454939074ac10f28bb1151dab3f648ee2fc12d", "generation_seconds_batch": 17.635579205933027, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4402986764907837, "target_z": 1.1093749935597295, "ce": 6.427689552307129, "genuineness": 4.105680465698242, "identity": 0.22697219252586365, "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_Amusement/a1ad54b397cfc1ea57f31207ad50ba9777acc058eafe37d28d2fe034b33fd003.mp3" }, { "id": "emo_Amusement-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-0", "key": "a1e5f21162eba770e28f26b24d7799dea686a6d915b013843ba1287c2373ed76", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "bd9eca5b26c81b85124fa44ae570920a098829788578e53098492084fd362fbf", "generation_seconds_batch": 22.453514160006307, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.131711483001709, "target_z": 1.9062498926621585, "ce": 5.879645347595215, "genuineness": 3.5220088958740234, "identity": 0.3212415874004364, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/a1e5f21162eba770e28f26b24d7799dea686a6d915b013843ba1287c2373ed76.mp3" }, { "id": "emo_Amusement-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-0", "key": "a295cde33546cd7cc6b038cac3b09e62de8d9a1ba7c9934b1e172d8b08327473", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ac2b301c0b8b8beabc8e7f55552b16bc0e095d2cbd011ad8b79a0866e26de2b3", "generation_seconds_batch": 17.612412122893147, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.348625421524048, "target_z": 2.1562499957064865, "ce": 6.252951145172119, "genuineness": 4.645420074462891, "identity": 0.6698630452156067, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/a295cde33546cd7cc6b038cac3b09e62de8d9a1ba7c9934b1e172d8b08327473.mp3" }, { "id": "emo_Amusement-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-1", "key": "a2efc765e17a73879bfd8fd8ffba03c39547386a5aad279c8b7c550e7319f8bc", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "b06d0ebe514a9febd765ee26ff64fde284cd8e88a51366316159db1437ce6051", "generation_seconds_batch": 24.48272975999862, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9080191850662231, "target_z": 1.6484375182474331, "ce": 6.324435234069824, "genuineness": 4.7458367347717285, "identity": 0.8062783479690552, "hypothesis": "J'ai trouvé la 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_Amusement/a2efc765e17a73879bfd8fd8ffba03c39547386a5aad279c8b7c550e7319f8bc.mp3" }, { "id": "emo_Amusement-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-1", "key": "a34cb432a442dd917289d366c3057bd5ae5dbd5f56f686fd7eb35aca77adb359", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "7d4cb2e27da4cb8a0e33de67e968bd943d20067cffc89cdab6ff241d8ce43b65", "generation_seconds_batch": 17.265696394024417, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.497753620147705, "target_z": 2.32812491198297, "ce": 5.895530700683594, "genuineness": 4.174716949462891, "identity": 0.47923022508621216, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/a34cb432a442dd917289d366c3057bd5ae5dbd5f56f686fd7eb35aca77adb359.mp3" }, { "id": "emo_Amusement-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-1", "key": "a4260315211a2bdadb0c036d0f05119afb6885d809abc72c6124b10d452b390c", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "2e43dc15083621bf8443fb8e418cd3d02e4cd1d08552b366666463b542d694c8", "generation_seconds_batch": 22.623030257993378, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3350682258605957, "target_z": 2.140624903395943, "ce": 6.038498878479004, "genuineness": 4.055472373962402, "identity": 0.556660532951355, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/a4260315211a2bdadb0c036d0f05119afb6885d809abc72c6124b10d452b390c.mp3" }, { "id": "emo_Amusement-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-1", "key": "a4c013f35c62234a6cc1017aafbfdf59322a2fe55e506a5b70bb7996647eacd3", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "1639bef2083f2813a7b04a3c45709583ed04363f793a7530f35bed79834695bb", "generation_seconds_batch": 17.67168299900368, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5487556457519531, "target_z": 1.2343750450818936, "ce": 6.419747352600098, "genuineness": 4.099404335021973, "identity": 0.49665528535842896, "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_Amusement/a4c013f35c62234a6cc1017aafbfdf59322a2fe55e506a5b70bb7996647eacd3.mp3" }, { "id": "emo_Amusement-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-1", "key": "a57de1e7038f2aef821f7e5d0d837a06eda534c3c8108c78f11c2c75fba0b4fd", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I found the little box.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It was beside the old window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "ab09cec83ed4645d29000efdc55eabb0d0c4259adcbd4848f6e36ae67a12bdce", "generation_seconds_batch": 24.56803324702196, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.179161548614502, "target_z": 1.9609375783566243, "ce": 6.268836498260498, "genuineness": 4.149612903594971, "identity": 0.6077505350112915, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/a57de1e7038f2aef821f7e5d0d837a06eda534c3c8108c78f11c2c75fba0b4fd.mp3" }, { "id": "emo_Amusement-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-1", "key": "a5e544de3729e90dd294dbc266405656a8b3c803c52a99fd3066a6caf303562c", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "5f709ebc09ed3818185690631d2cc60cc023064981a1d59a2fb89e748ffd4170", "generation_seconds_batch": 23.361566098988988, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4470772743225098, "target_z": 1.1171875397150013, "ce": 6.125868320465088, "genuineness": 3.773050308227539, "identity": 0.5036239624023438, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/a5e544de3729e90dd294dbc266405656a8b3c803c52a99fd3066a6caf303562c.mp3" }, { "id": "emo_Amusement-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-0", "key": "a6a32ad3f4e85d8dae7be575d9bc1cc121f38a1ebc39f2321bace58a5b3e10ad", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The door is still open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "212715aeafef8e39b9bac5ed1fc1ec0bc54332816aedeb1e83546699b6194b46", "generation_seconds_batch": 17.65625928598456, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5655391216278076, "target_z": 2.40624982396594, "ce": 6.268836498260498, "genuineness": 3.7667744159698486, "identity": 0.4742690324783325, "hypothesis": "The door's still open. I put your coat on the chair. Tell me when you are ready", "wer": 0.1111111111111111, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/a6a32ad3f4e85d8dae7be575d9bc1cc121f38a1ebc39f2321bace58a5b3e10ad.mp3" }, { "id": "emo_Amusement-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-1", "key": "a764b50c4566372100d9e87224e5573c21c0c4384bd0365d1c0f76660f2de320", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "1d49d8ecc472471c85cb73c7a4738e36cc2d8030d015f31608e188cb1def1f3f", "generation_seconds_batch": 24.225773444981314, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9690262079238892, "target_z": 1.7187500214675684, "ce": 6.221180438995361, "genuineness": 4.319066047668457, "identity": 0.7350916266441345, "hypothesis": "J'ai trouvé la 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_Amusement/a764b50c4566372100d9e87224e5573c21c0c4384bd0365d1c0f76660f2de320.mp3" }, { "id": "emo_Amusement-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-1", "key": "a766ed6ddc2a6a3d5748bd9a52f6a65ee462ac62ff01638722b8675338095353", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "161864bba96b379efacb2a301b03ab4ab857c2cdf62a603068bf14e7c7fb6969", "generation_seconds_batch": 18.014813481946476, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3079540729522705, "target_z": 2.1093749935597295, "ce": 6.133810997009277, "genuineness": 4.287685871124268, "identity": 0.6596938371658325, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/a766ed6ddc2a6a3d5748bd9a52f6a65ee462ac62ff01638722b8675338095353.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": "a7a09035b1e52bde67fe324451a446d1e5fd224e3d6a68d5baeae88dfd3d463b", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "34f5fec9b3dc3a678900781cb9c25a45edb4d4b7c35523a58f3f999631dd5ecf", "generation_seconds_batch": 20.23383317294065, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.714667558670044, "target_z": 2.5781250150272976, "ce": 6.395919322967529, "genuineness": 4.18099308013916, "identity": 0.5214786529541016, "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_Amusement/a7a09035b1e52bde67fe324451a446d1e5fd224e3d6a68d5baeae88dfd3d463b.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_Amusement", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": "af37b7dd45f23e083fef844ec69da96ee0591bc6567d301a3fc8293442c1b30b", "generation_seconds_batch": 17.39465751789976, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9725781679153442, "target_z": 0.5703124688720259, "ce": 6.125868320465088, "genuineness": 4.319066047668457, "identity": 0.6317718029022217, "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_Amusement/a8bd001b1fcafd2f49b65d73e6ed12567e4c9664909a4d08700c9febfd977540.mp3" }, { "id": "emo_Amusement-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-1", "key": "a92b5c2736fb3ba7ab74739991dca1b9efb70fbb874e3a299234d809b0947af4", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "a222ecddc3e604a88bd778237452f95cbc3399f581c5a01b7311553096a65ac6", "generation_seconds_batch": 23.55016153305769, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7724480628967285, "target_z": 1.492187556889056, "ce": 6.229123115539551, "genuineness": 4.6705241203308105, "identity": 0.4935668706893921, "hypothesis": "J'ai trouvé la 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_Amusement/a92b5c2736fb3ba7ab74739991dca1b9efb70fbb874e3a299234d809b0947af4.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_Amusement", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e7ba5411757ab61ea278a91720a29f73cfa25149b40b19f35ad8987735c55d46", "generation_seconds_batch": 16.6870182499988, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6692377328872681, "target_z": 0.220703123658277, "ce": 6.1894097328186035, "genuineness": 4.519899368286133, "identity": 0.7710509896278381, "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_Amusement/a94b7d5da78ff217f8e5a4f7ae4520900bef0ad764d0e4ee898e69de10c28aea.mp3" }, { "id": "emo_Amusement-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-1", "key": "a97ee2ea3a135a23a4c016c17563d23eed26dd93e15c40355db496e9bd871e65", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I found the little box.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It was beside the old window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "3206edc5b74c781c28e1c1e255fe755663c69941aa845e0967a99710e85c91d4", "generation_seconds_batch": 24.767315716017038, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4299681186676025, "target_z": 2.25, "ce": 6.38797664642334, "genuineness": 3.9801597595214844, "identity": 0.43598416447639465, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/a97ee2ea3a135a23a4c016c17563d23eed26dd93e15c40355db496e9bd871e65.mp3" }, { "id": "emo_Amusement-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-1", "key": "a9d816e6ce750686f487b2c5db2d1dd14b3e6ec989c7d027fa075aa19af4bad6", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "58c8fb1945673581e6a0fc1c98ce2114240d376150ca0ce509575a9b14f4c070", "generation_seconds_batch": 16.974856312968768, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.192718505859375, "target_z": 1.9765623958822938, "ce": 6.3641486167907715, "genuineness": 4.406930446624756, "identity": 0.4898849129676819, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/a9d816e6ce750686f487b2c5db2d1dd14b3e6ec989c7d027fa075aa19af4bad6.mp3" }, { "id": "emo_Amusement-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-0", "key": "a9e667238171c7dff07a7304f9152ac98f7304222862bef328319791e3ecd66b", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "8a7260e7f2c764c3c987f62f60f2e7432a22851aba928e0d5e9a663695f59886", "generation_seconds_batch": 16.88433630100917, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8673478364944458, "target_z": 1.6015625161006761, "ce": 6.157639026641846, "genuineness": 4.519899368286133, "identity": 0.5406622886657715, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt. Hein?", "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_Amusement/a9e667238171c7dff07a7304f9152ac98f7304222862bef328319791e3ecd66b.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": "a9eda8d85f29cbf65975a4dd6933bf58c4286b63e226125c937feb63a58876e3", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Escribí el número en el sobre.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6eb7d5ac963cdeb892290c5dcbb0ceb6e3b4bb5ca519b8c389719b9ae3796f74", "generation_seconds_batch": 15.198533010086976, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3148953914642334, "target_z": 0.9648437827380417, "ce": 6.157639026641846, "genuineness": 4.168440818786621, "identity": 0.6113436818122864, "hypothesis": "Escribí el número en el sobre, léelelo bien, y comprueba las dos últimas cifras. Llámame cuando tengas un momento.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/a9eda8d85f29cbf65975a4dd6933bf58c4286b63e226125c937feb63a58876e3.mp3" }, { "id": "emo_Amusement-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-0", "key": "aa2e4941b382ca383a88afb82e5b8cbdfa439cb031f71464a1c5519449110f30", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "1a075a2b4d8f10722a172f26d7e9a35ee8369d6825f41fddf8bd73addf404fb1", "generation_seconds_batch": 24.071870076004416, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.352177381515503, "target_z": 1.007812443110944, "ce": 6.292664527893066, "genuineness": 4.362998008728027, "identity": 0.6299906969070435, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/aa2e4941b382ca383a88afb82e5b8cbdfa439cb031f71464a1c5519449110f30.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_Amusement", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5a8bed20d04dbf2f161040e95e46a0e7d232a16c9a8b914bc90d76b59ab2e404", "generation_seconds_batch": 17.845964765991084, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2887911796569824, "target_z": -0.21777343602410468, "ce": 6.507116317749023, "genuineness": 4.331617832183838, "identity": 0.3826240599155426, "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_Amusement/ab7a94299f968552a7b966fa3391724b652d8e20483888a7767196f29a7f4a69.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": "abe4e7dc2803ded665948addfdb00d0e094402f607b1805df1534b1c89200f17", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "62a701743ddba6f3d0435ffea8a96d9527a876c588b5f48af5fa6f5d85cf47c7", "generation_seconds_batch": 15.213280186988413, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.758890986442566, "target_z": 1.4765626019709495, "ce": 6.173524379730225, "genuineness": 4.469690799713135, "identity": 0.38798287510871887, "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_Amusement/abe4e7dc2803ded665948addfdb00d0e094402f607b1805df1534b1c89200f17.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": "ac44c1496b7652b31fa6a6b983e7ecf2ac066f87fcadcf69e7cad828e2690ff4", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "93fb5d65fc3765b2f210d9e636b6355a24959d4f3892396358746d10bab3010f", "generation_seconds_batch": 15.08638767094817, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.741781711578369, "target_z": 2.609374924863511, "ce": 6.356205940246582, "genuineness": 4.381826400756836, "identity": 0.5674973130226135, "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_Amusement/ac44c1496b7652b31fa6a6b983e7ecf2ac066f87fcadcf69e7cad828e2690ff4.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": "ac97087389105b5975bee95b810ecc99f2c6e3333a0d3262a71b0a88c73458a3", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Your message arrived after I had left.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1061c6f8c7c8009adcbc45084c59369b77a7d57ce6513f19a23e4e90f9be4861", "generation_seconds_batch": 24.785941154928878, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3318417072296143, "target_z": 0.9843749420375656, "ce": 6.403861999511719, "genuineness": 4.099404335021973, "identity": 0.3703899085521698, "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_Amusement/ac97087389105b5975bee95b810ecc99f2c6e3333a0d3262a71b0a88c73458a3.mp3" }, { "id": "emo_Amusement-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-0", "key": "acca35bc2df2cc735546467eb32029ec13ae30a1f4f4ad874977bf6029a7eb2f", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "1cdf113e4f1654749df2054b16d3da52101e31109ba4c2919904352b99e8025b", "generation_seconds_batch": 24.144701690995134, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0368118286132812, "target_z": 1.7968750708429755, "ce": 6.221180438995361, "genuineness": 4.519899368286133, "identity": 0.6201517581939697, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/acca35bc2df2cc735546467eb32029ec13ae30a1f4f4ad874977bf6029a7eb2f.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": "acd4cc00eca4ba7d574c87af18f6909d4ab5dd106bc2449f86defa50329f2ee9", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Your message arrived after I had left.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f228d8df21d58a3952aecf36977ace88456f05438741df223de022e37b519516", "generation_seconds_batch": 16.524685540003702, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9827460050582886, "target_z": 0.5820312194087152, "ce": 6.435632705688477, "genuineness": 4.293961524963379, "identity": 0.3646159768104553, "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_Amusement/acd4cc00eca4ba7d574c87af18f6909d4ab5dd106bc2449f86defa50329f2ee9.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": "acf084524f2515897e275b37607e647f20974c689b7056e14f4a50792a3883e5", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d0fc24e764177aaad904f586710e27d45eaa843103aaf92e56d44d73a3e3788b", "generation_seconds_batch": 18.277612935984507, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0774831771850586, "target_z": 1.8437500729897323, "ce": 6.046441555023193, "genuineness": 4.356721878051758, "identity": 0.6501715779304504, "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_Amusement/acf084524f2515897e275b37607e647f20974c689b7056e14f4a50792a3883e5.mp3" }, { "id": "emo_Amusement-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-0", "key": "ad7d30f10e7f0d8323514d60aa557b05fd899dd47de460f60b4cf91d85033508", "bucket": "emo_Amusement", "phase": "wording", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "ca74e330289aef0bd270a92166184c6cdeec0cdf54c8045c973e378d0940656e", "generation_seconds_batch": 17.71025672298856, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3420095443725586, "target_z": 0.9960936925742547, "ce": 5.998785495758057, "genuineness": 3.8420867919921875, "identity": 0.26506882905960083, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/ad7d30f10e7f0d8323514d60aa557b05fd899dd47de460f60b4cf91d85033508.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_Amusement", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": "66409e314222d435725b85ce298e1a5c9bc106702b2afae889b2893ce6f56751", "generation_seconds_batch": 17.87232257204596, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.26744544506073, "target_z": 0.910156234436013, "ce": 6.022613525390625, "genuineness": 4.532451152801514, "identity": 0.572989284992218, "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_Amusement/adcc0121d6c11de6953f8243f84ad890832f75283c96342c1db246fddc443438.mp3" }, { "id": "emo_Amusement-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-0", "key": "adfeafea0d3bbb7db3668602aabdb57072ed4d5dba3db8f81ff04f2ad1bdc81c", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The door is still open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "cd1b56a80f272d30d0fcc764435e661ee0fb0324120d7898e11727f05165a765", "generation_seconds_batch": 24.18833259504754, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3350682258605957, "target_z": 2.140624903395943, "ce": 6.1020402908325195, "genuineness": 3.810706615447998, "identity": 0.40015292167663574, "hypothesis": "The door's still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.1111111111111111, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/adfeafea0d3bbb7db3668602aabdb57072ed4d5dba3db8f81ff04f2ad1bdc81c.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_Amusement", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": "8f7b48d0b8a1250af92429d8725777f2d4ab37a0660248ed5ce27dbd41f0bd5a", "generation_seconds_batch": 17.03795072308276, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1794869303703308, "target_z": -0.34375000429351366, "ce": 6.4515180587768555, "genuineness": 4.268857479095459, "identity": 0.42585301399230957, "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_Amusement/ae3130a5db36c2790a31e23135fde257111c56fa9c5b8061c1f3e51a8cb61258.mp3" }, { "id": "emo_Amusement-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-1", "key": "ae655bd1d77442c59e6ab3939aecaa0efc7320c869a7fb4dbff28b73f4b25f78", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "4e7ef15887572567c382aa808333f5f3159e5d7d73ebf321f08b1d2d6fb05fdc", "generation_seconds_batch": 18.701121035963297, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5894269943237305, "target_z": 1.2812500472286503, "ce": 6.300607204437256, "genuineness": 4.457139015197754, "identity": 0.6792145371437073, "hypothesis": "J'ai trouvé la 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_Amusement/ae655bd1d77442c59e6ab3939aecaa0efc7320c869a7fb4dbff28b73f4b25f78.mp3" }, { "id": "emo_Amusement-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-1", "key": "ae9fd3c366ed53eaeefa9495148e11b75478c10e196852260985c8ac0c5da49e", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "de001b5e3d76754a7d74a2534a75749bb8f75d233527e90effe01039bebdb1b0", "generation_seconds_batch": 24.223225228022784, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8537907600402832, "target_z": 1.5859375611825697, "ce": 6.483288764953613, "genuineness": 4.331617832183838, "identity": 0.6040881872177124, "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_Amusement/ae9fd3c366ed53eaeefa9495148e11b75478c10e196852260985c8ac0c5da49e.mp3" }, { "id": "emo_Amusement-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-0", "key": "aea88538dca9937a2c53b8c79ed12b2702a15f8b67a16512ab5e5f25c1fc4ee2", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "783a54474f1d28b6c654389dc64429bd4648f2a6bf3b8ecb5b92dae412f4a032", "generation_seconds_batch": 21.487364273983985, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7182196378707886, "target_z": 1.4296875998241927, "ce": 6.1894097328186035, "genuineness": 4.519899368286133, "identity": 0.6474168300628662, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/aea88538dca9937a2c53b8c79ed12b2702a15f8b67a16512ab5e5f25c1fc4ee2.mp3" }, { "id": "emo_Amusement-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-0", "key": "af4e104bbc3734369069e20bb9dd8e984dca83d3f763686ce691ffab89291aee", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "94f29097e05eec73e6447e3dcc59ce684de99ae1bee55917ba0f74129547cfe6", "generation_seconds_batch": 24.05707928701304, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.267282724380493, "target_z": 2.0624999914129725, "ce": 6.062326908111572, "genuineness": 4.055472373962402, "identity": 0.5422872304916382, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/af4e104bbc3734369069e20bb9dd8e984dca83d3f763686ce691ffab89291aee.mp3" }, { "id": "emo_Amusement-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-1", "key": "afdc617739fb77b52c3d5007a3e65f8345281dfd0d840cb6dfd59a624da06c89", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I found the little box.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It was beside the old window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "2bbad448723a466b2823e7df32775f15745468781c2da24fc37771ec8ba9530c", "generation_seconds_batch": 23.818493850063533, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7553389072418213, "target_z": 2.6250000171740546, "ce": 6.38003396987915, "genuineness": 4.168440818786621, "identity": 0.493216335773468, "hypothesis": "I found the little box. It was beside the old window. We can look inside together,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/afdc617739fb77b52c3d5007a3e65f8345281dfd0d840cb6dfd59a624da06c89.mp3" }, { "id": "emo_Amusement-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-1", "key": "b0712e10e26f52437b3375bf9c5d6f2e5bc8cb22430163334bf8d1feba96835e", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "97774a9f8f9a89eec330ebca6eab0e296b062b58c231fcfcefb416a65822188e", "generation_seconds_batch": 25.11776234197896, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.962247610092163, "target_z": 1.7109374753122963, "ce": 6.117925643920898, "genuineness": 4.381826400756836, "identity": 0.6934251189231873, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/b0712e10e26f52437b3375bf9c5d6f2e5bc8cb22430163334bf8d1feba96835e.mp3" }, { "id": "emo_Amusement-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-1", "key": "b09245da24052d20f53a70372eec7b417010a70f3292978f44e5235cedab2e87", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 1.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "97548be66f1b30618e7778887a7f6667912f0c2585381b64c309f4c9352da931", "generation_seconds_batch": 21.910750183975324, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7860051393508911, "target_z": 1.5078125118071626, "ce": 6.467403411865234, "genuineness": 4.293961524963379, "identity": 0.6314784288406372, "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_Amusement/b09245da24052d20f53a70372eec7b417010a70f3292978f44e5235cedab2e87.mp3" }, { "id": "emo_Amusement-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-1", "key": "b0ee4393782d24a461e20dbbf983e6260cd81b416a0b6436312283e6e59f755f", "bucket": "emo_Amusement", "phase": "wording", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "48c970d2f8226b1baed5b4fde32d559212a43363755064d771f93cc9f334c41a", "generation_seconds_batch": 15.499376502004452, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8302284479141235, "target_z": 0.40624996135837704, "ce": 6.292664527893066, "genuineness": 4.557555198669434, "identity": 0.5428177714347839, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/b0ee4393782d24a461e20dbbf983e6260cd81b416a0b6436312283e6e59f755f.mp3" }, { "id": "emo_Amusement-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-0", "key": "b2332e073cee80451cd0df30c432bb3dc1b122f9b5f10e4863adec86c23d2113", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "791b9c7d61eb10b5145eea9ea068c454d499543c4fd3ab5359be260159546813", "generation_seconds_batch": 16.934897080995142, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9283548593521118, "target_z": 1.6718750193208114, "ce": 6.23706579208374, "genuineness": 4.149612903594971, "identity": 0.5713558793067932, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/b2332e073cee80451cd0df30c432bb3dc1b122f9b5f10e4863adec86c23d2113.mp3" }, { "id": "emo_Amusement-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-0", "key": "b23405b997ad2bd7ffa32db731e058f2f386bdb88bdd35d8a0539bdf4795ef48", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "1c6bd94d01ca7a51270a40f28dcf06a6d32163dd58fb0948ee6e6df7909b42a6", "generation_seconds_batch": 23.113799753948115, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3453989028930664, "target_z": 1.0000000343481092, "ce": 6.24500846862793, "genuineness": 4.250029563903809, "identity": 0.4016294479370117, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/b23405b997ad2bd7ffa32db731e058f2f386bdb88bdd35d8a0539bdf4795ef48.mp3" }, { "id": "emo_Amusement-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-1", "key": "b31018053a3bbf57e039b8ba16aea11f9678f9c02e23d38677e5ac56730a440e", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "6fc78bd03d1a8fbcc53b3d6ee1cc85ac7d28781615d26cf8b0249fb397e1d216", "generation_seconds_batch": 24.76977893000003, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.226611375808716, "target_z": 2.015624989266216, "ce": 6.197352409362793, "genuineness": 4.193545341491699, "identity": 0.6460584402084351, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos? ¿Veo qué hay dentro?", "wer": 0.11764705882352941, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/b31018053a3bbf57e039b8ba16aea11f9678f9c02e23d38677e5ac56730a440e.mp3" }, { "id": "emo_Amusement-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-1", "key": "b37f5c9837a94d7f1b8ee669ac4f0395022293829a43d60d566fc17f158918b3", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "fb91438f0f1b4a9111f94ae30eec024cbb2bb14dc0815884baebe0caca42cad7", "generation_seconds_batch": 23.402226174017414, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7724480628967285, "target_z": 1.492187556889056, "ce": 6.55477237701416, "genuineness": 4.042920112609863, "identity": 0.5036621689796448, "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_Amusement/b37f5c9837a94d7f1b8ee669ac4f0395022293829a43d60d566fc17f158918b3.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": "b3953c44da270411ce4f11e7a8332c8b815d933f65051962921a2ed0c4768f2a", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Escribí el número en el sobre.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bfd2eb7756d7392241b815b4c5b13720be9afcacf3df9d186ebccae6ae1d2ff3", "generation_seconds_batch": 26.913656300050206, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2130541801452637, "target_z": 1.999999896955672, "ce": 6.149696350097656, "genuineness": 4.218649387359619, "identity": 0.4906828999519348, "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_Amusement/b3953c44da270411ce4f11e7a8332c8b815d933f65051962921a2ed0c4768f2a.mp3" }, { "id": "emo_Amusement-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-0", "key": "b3acfe37709d66e3bb4cce522dab16b8b47b4524e68800de9d3d5da1de323612", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "80b50b94cdea481e41a8b688413fcf4171464bac2b357e1fd964b71c706434a5", "generation_seconds_batch": 24.417220689938404, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2640562057495117, "target_z": 0.9062500300545956, "ce": 6.1020402908325195, "genuineness": 4.2374773025512695, "identity": 0.4905005991458893, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/b3acfe37709d66e3bb4cce522dab16b8b47b4524e68800de9d3d5da1de323612.mp3" }, { "id": "emo_Amusement-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-1", "key": "b3c12b29389deb84d917e546746282e917fc7fa200a11ca2c57bc57b3a225b45", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "c94d8b79c9e0cdf390e898db0dae7f54c36e8ff448f8114dce4197b34c630e29", "generation_seconds_batch": 16.794722120976076, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.389296770095825, "target_z": 2.203124997853243, "ce": 6.133810997009277, "genuineness": 4.444586753845215, "identity": 0.5888431668281555, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/b3c12b29389deb84d917e546746282e917fc7fa200a11ca2c57bc57b3a225b45.mp3" }, { "id": "emo_Amusement-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-0", "key": "b3fe936a61a8c167700e1a8341cb7caf9e17439f90523f3e7a210601f2fedd60", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "482b4b028ca692b8a4d524ad5eaea26bc895f52bbfb522af7594207ea5beedf0", "generation_seconds_batch": 25.29698006203398, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9893618822097778, "target_z": 1.7421875225409467, "ce": 6.078212261199951, "genuineness": 3.9801597595214844, "identity": 0.670107364654541, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/b3fe936a61a8c167700e1a8341cb7caf9e17439f90523f3e7a210601f2fedd60.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_Amusement", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": "5c7d15abac4d87c43eee75c0cdf8a5c9ba4baccc632e36b27f16b883c783b6ff", "generation_seconds_batch": 18.587327846093103, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5177793502807617, "target_z": 0.0461425974122684, "ce": 6.229123115539551, "genuineness": 4.287685871124268, "identity": 0.5281161069869995, "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_Amusement/b429ad869b4f073af736e4e6510807542fc4f5324b0eb7f096c719d9002f4f71.mp3" }, { "id": "emo_Amusement-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-0", "key": "b4f2d85ce768f1d281c73bef725b98bb781358d467e969984d7a8bd127fadc45", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "e4583f32049895b07766650d33d1cbe928bf8d02d60c49ca338b272920ac3959", "generation_seconds_batch": 22.5930978290271, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5384249687194824, "target_z": 2.374999914129727, "ce": 5.569881439208984, "genuineness": 3.525146961212158, "identity": 0.5143390893936157, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/b4f2d85ce768f1d281c73bef725b98bb781358d467e969984d7a8bd127fadc45.mp3" }, { "id": "emo_Amusement-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-1", "key": "b4fb9a41214b547ef14a8bdd4adc5f52da6e71074f4ca60a0e37282fbbf7313e", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "50d3ee7b10a06a17a40809e421d078d49350e6a0b76eeb3a115cc700be0ac03c", "generation_seconds_batch": 25.973652609973215, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5962055921554565, "target_z": 1.2890625933839222, "ce": 6.292664527893066, "genuineness": 4.457139015197754, "identity": 0.5989668369293213, "hypothesis": "J'ai trouvé la 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_Amusement/b4fb9a41214b547ef14a8bdd4adc5f52da6e71074f4ca60a0e37282fbbf7313e.mp3" }, { "id": "emo_Amusement-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-0", "key": "b5a5791352afc27d8745b0dc32112f48c5a8d87dac0e5c484094dae570101e29", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "a30e722ad63dd4921595825886eada9fcce5a7d88ca6172d14d03194700221d0", "generation_seconds_batch": 22.622653793892823, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2030491828918457, "target_z": 0.8359375268344604, "ce": 6.229123115539551, "genuineness": 4.444586753845215, "identity": 0.4973636269569397, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/b5a5791352afc27d8745b0dc32112f48c5a8d87dac0e5c484094dae570101e29.mp3" }, { "id": "emo_Amusement-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-1", "key": "b63dc227addf5d47c931b3ac6fff19abda45bc0b2e9cdba5a9df623f71002cb5", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "7230ea69fa5b3ff2a6895d1e81168a7427ded8dc7d742b9d1c74a51608d00bc4", "generation_seconds_batch": 18.055171277956106, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4470772743225098, "target_z": 1.1171875397150013, "ce": 6.24500846862793, "genuineness": 4.369274139404297, "identity": 0.7292340397834778, "hypothesis": "J'ai trouvé la 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_Amusement/b63dc227addf5d47c931b3ac6fff19abda45bc0b2e9cdba5a9df623f71002cb5.mp3" }, { "id": "emo_Amusement-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-1", "key": "b66c95aff73bacbb9ec3ddee6dba424515f5c706f16ef18c3f0ebf6db1479502", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I found the little box.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It was beside the old window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "7a61c10fe552b6826fdf93cbd671ef9e97d0891d18a46529efc24386a6d4ac2f", "generation_seconds_batch": 21.261982748052105, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.619767665863037, "target_z": 2.4687499184232404, "ce": 6.221180438995361, "genuineness": 4.262581825256348, "identity": 0.5674225091934204, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/b66c95aff73bacbb9ec3ddee6dba424515f5c706f16ef18c3f0ebf6db1479502.mp3" }, { "id": "emo_Amusement-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-1", "key": "b67ddb5662a1526358dbdf004932713fbfe067d3e45f8036656ae5684a3cc6da", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "bd21c354406e461ed3284b82dba72732a0de062da40b07ff5e62dc9174b104f7", "generation_seconds_batch": 21.925576448091306, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7960102558135986, "target_z": 2.6718750193208116, "ce": 6.157639026641846, "genuineness": 3.9927117824554443, "identity": 0.3773539066314697, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/b67ddb5662a1526358dbdf004932713fbfe067d3e45f8036656ae5684a3cc6da.mp3" }, { "id": "emo_Amusement-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-1", "key": "b68d3139819f477e6c126dbd36980c400faec9c784f4bfd2e7e98ba69b16ce41", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "e91098cb16f5783fafcd3e947a0dc3c4e6b75a2d2e721ac52347e5ae207ae179", "generation_seconds_batch": 23.485434069065377, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1349380016326904, "target_z": 3.0624998540205355, "ce": 6.141753673553467, "genuineness": 4.532451152801514, "identity": 0.6829811334609985, "hypothesis": "Hihihi! 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_Amusement/b68d3139819f477e6c126dbd36980c400faec9c784f4bfd2e7e98ba69b16ce41.mp3" }, { "id": "emo_Amusement-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-0", "key": "b6c39a9c6e53e8f41f887c615292d49f275e91e9b1b3a681fa412cbcf26de180", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "b928b9629cfd33cca054431d69ca41d3bde4af72c5132f3a1b2ec9ba1faaeaa7", "generation_seconds_batch": 24.1472569280304, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9044671058654785, "target_z": 2.796874933450538, "ce": 5.6413655281066895, "genuineness": 3.6914620399475098, "identity": 0.4285193979740143, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listos.", "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_Amusement/b6c39a9c6e53e8f41f887c615292d49f275e91e9b1b3a681fa412cbcf26de180.mp3" }, { "id": "emo_Amusement-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-1", "key": "b6d71ecc0e3ff0738c7ceb35350eb154ce814eede548c8952e808e95399225cb", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "45c2a137c027491cf18c9a32805a7a2c768b25080ed9c9b37bffabe9cba63605", "generation_seconds_batch": 26.884755780920386, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4435253143310547, "target_z": 2.2656250923105437, "ce": 6.213237762451172, "genuineness": 4.256305694580078, "identity": 0.49460506439208984, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble what contient.", "wer": 0.10526315789473684, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/b6d71ecc0e3ff0738c7ceb35350eb154ce814eede548c8952e808e95399225cb.mp3" }, { "id": "emo_Amusement-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-1", "key": "b75ed94d74809b3c0862a930b139e35b9f052e81ccecc09b2e8747c76286cf32", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3e4abea95713b638e8e83f04e827aadd697f8c619e6614bb4a5204254c865579", "generation_seconds_batch": 15.943938676966354, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5113108158111572, "target_z": 2.3437500042935135, "ce": 6.229123115539551, "genuineness": 4.030367851257324, "identity": 0.4409462809562683, "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_Amusement/b75ed94d74809b3c0862a930b139e35b9f052e81ccecc09b2e8747c76286cf32.mp3" }, { "id": "emo_Amusement-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-0", "key": "b77334e592a9befa1aedc5ad005536c7587d358159b0d2151059123bce950cba", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "0a7ee6e838d60bf647f5ab010ccdd67b95b728fbd2f9b02bce62abfc67cf7b09", "generation_seconds_batch": 20.37081340001896, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.226611375808716, "target_z": 2.015624989266216, "ce": 6.260893821716309, "genuineness": 4.268857479095459, "identity": 0.5411545038223267, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/b77334e592a9befa1aedc5ad005536c7587d358159b0d2151059123bce950cba.mp3" }, { "id": "emo_Amusement-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-0", "key": "b7cb08702ee9eeb80f26883b0bc5e0dc043f11bff91c54c9c2abb3b5250ddcb3", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "bba4585d280779b62de9ba2422ec32595a277f035268df324019997079b3b5e8", "generation_seconds_batch": 19.185466383001767, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9217389822006226, "target_z": 0.5117187161885799, "ce": 6.205295085906982, "genuineness": 4.6203155517578125, "identity": 0.368973046541214, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/b7cb08702ee9eeb80f26883b0bc5e0dc043f11bff91c54c9c2abb3b5250ddcb3.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": "b8483a595c8e91ef79444ef221efdff034c5feceffafee9be3c6d856f626acf4", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d5eca9ef8fd77a6a129acfcabf808234f021ca81f2dea3a94b28fb0c16db3365", "generation_seconds_batch": 16.71423181402497, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7385553121566772, "target_z": 1.453125100897571, "ce": 6.1894097328186035, "genuineness": 4.369274139404297, "identity": 0.6421535015106201, "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_Amusement/b8483a595c8e91ef79444ef221efdff034c5feceffafee9be3c6d856f626acf4.mp3" }, { "id": "emo_Amusement-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-1", "key": "b8cff8681eaa522c528f5712602d66d7774f32b418cda8b79e65eb5e977830b7", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "6696556ea81636235c0b8fcb5bb66c61a8381ea2e1797ad9ede403fb8cd551fe", "generation_seconds_batch": 22.532279031933285, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1213808059692383, "target_z": 3.046874761709992, "ce": 5.927301406860352, "genuineness": 4.049196243286133, "identity": 0.22004728019237518, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/b8cff8681eaa522c528f5712602d66d7774f32b418cda8b79e65eb5e977830b7.mp3" }, { "id": "emo_Amusement-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-0", "key": "b8feaf3454309d9c055b3c4e0d5a62ea9d57ee80f93085a8d20b12147dde62b0", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5731630a2d267712f58c0cd0b23a51e37584c004dd4596079cfdc8dd69c1afe9", "generation_seconds_batch": 25.535106010036543, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.348625421524048, "target_z": 2.1562499957064865, "ce": 6.197352409362793, "genuineness": 4.344170093536377, "identity": 0.4140359163284302, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/b8feaf3454309d9c055b3c4e0d5a62ea9d57ee80f93085a8d20b12147dde62b0.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": "b900f5cb9e8b2dbd102854712701efa3ef1d97922135188b721b3f3eada6880d", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Your message arrived after I had left.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5c0e8bb18722da7107a8583e5a911657953747c6918fd53a7a4e8ab2b2a5d166", "generation_seconds_batch": 16.524685540003702, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6875531673431396, "target_z": 2.5468748304062103, "ce": 6.475345611572266, "genuineness": 4.281409740447998, "identity": 0.30325084924697876, "hypothesis": "Your message arrived after I had left. I read it twice, before putting the phone away. Let me know and we can talk.", "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_Amusement/b900f5cb9e8b2dbd102854712701efa3ef1d97922135188b721b3f3eada6880d.mp3" }, { "id": "emo_Amusement-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-1", "key": "b951a8a5fbbf09f19341773277874cfdb5d72dddd95c1a6c2fa44c279fa045fd", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "3120ab742682c8989f45b7618b3605771158e91dbbd7ed673f46e77c45ff2d7d", "generation_seconds_batch": 21.170096761896275, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8876835107803345, "target_z": 1.6250000171740546, "ce": 5.967014789581299, "genuineness": 4.344170093536377, "identity": 0.6637753248214722, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana, vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/b951a8a5fbbf09f19341773277874cfdb5d72dddd95c1a6c2fa44c279fa045fd.mp3" }, { "id": "emo_Amusement-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-1", "key": "b9e0932d2fe8eded9ed714bb9e0de899af55c48b0e0b2553d07ae41b5155edff", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "787fbd43d365ffade6aaa6127ddea1c73ac8c9246ab4faac8d0f88f0b4441c38", "generation_seconds_batch": 21.720479234005325, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6468818187713623, "target_z": 2.4999998282594533, "ce": 6.0305562019348145, "genuineness": 3.886019229888916, "identity": 0.41248682141304016, "hypothesis": "Ik heb het kleine doodje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/b9e0932d2fe8eded9ed714bb9e0de899af55c48b0e0b2553d07ae41b5155edff.mp3" }, { "id": "emo_Amusement-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-0", "key": "ba100e877fe529b568711de727961963fbdbf2bcfac9de5812c6ab572f1dab2c", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The door is still open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9bf70fca9f16f1d8fed30de8b1bb27196d2833154a291d496f7f8a2a2d0ab155", "generation_seconds_batch": 25.69331979297567, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7317767143249512, "target_z": 1.4453125547422991, "ce": 6.316492557525635, "genuineness": 3.9676074981689453, "identity": 0.13769860565662384, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/ba100e877fe529b568711de727961963fbdbf2bcfac9de5812c6ab572f1dab2c.mp3" }, { "id": "emo_Amusement-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-0", "key": "ba3767f3aa0f85584cc0de3ee9c76eb7b174e8aa64c5cdf5004922747d7a1b01", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7e55a44fa3a2d7a52e6cfa694c71127c7e10bb13308218eb9ab481fd8c6a1da0", "generation_seconds_batch": 24.63210084394086, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5758699178695679, "target_z": 1.2656250923105437, "ce": 6.300607204437256, "genuineness": 4.482243061065674, "identity": 0.5140911340713501, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/ba3767f3aa0f85584cc0de3ee9c76eb7b174e8aa64c5cdf5004922747d7a1b01.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_Amusement", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": "9db4cc516ea31d62d0ef0917c99ed7ecd39a8f21106793860948eee3cdc42db0", "generation_seconds_batch": 16.94844940607436, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8607319593429565, "target_z": 0.4414062129684447, "ce": 6.1020402908325195, "genuineness": 4.319066047668457, "identity": 0.6808534860610962, "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_Amusement/ba70e7e208a6b15a9236ccd5a69e0e5fd403df2a937202d690effa2cdc45d9f2.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": "ba79389099e4e3a9ae122371301a0a1b5e3ff35d1957e931beaf5bdd5911e086", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The keys are on the kitchen table.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f89d18e50bd77e70eed2c3023d00926412e4a64825b7a4e601e35c52097ca427", "generation_seconds_batch": 18.586985579924658, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9554691314697266, "target_z": 1.7031250665494617, "ce": 6.356205940246582, "genuineness": 4.042920112609863, "identity": 0.22552597522735596, "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_Amusement/ba79389099e4e3a9ae122371301a0a1b5e3ff35d1957e931beaf5bdd5911e086.mp3" }, { "id": "emo_Amusement-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-1", "key": "baffe1196b1a7e35d4a69bd88d2e29f1ea33643a7b49564b870cdccae9eba474", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "948fee21b3a63fedc1214962a049c45f054f901756f386275afc64715a5c7465", "generation_seconds_batch": 17.78785705100745, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.094266653060913, "target_z": 3.0156248518737785, "ce": 6.022613525390625, "genuineness": 4.369274139404297, "identity": 0.27958589792251587, "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_Amusement/baffe1196b1a7e35d4a69bd88d2e29f1ea33643a7b49564b870cdccae9eba474.mp3" }, { "id": "emo_Amusement-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-0", "key": "bb17e5ebb05426aa99d0b8bb050617d3985fa1d7ff2cc26a113e81b40f713b2c", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De deur staat nog open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "856af55b20ed814364710f578bedbb23dfc56e9a1f0bdd412269e12513c6bfef", "generation_seconds_batch": 22.901566465967335, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.606210470199585, "target_z": 2.4531248261126968, "ce": 5.792276382446289, "genuineness": 4.162164688110352, "identity": 0.0950632095336914, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/bb17e5ebb05426aa99d0b8bb050617d3985fa1d7ff2cc26a113e81b40f713b2c.mp3" }, { "id": "emo_Amusement-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-0", "key": "bb621bc9f16f14fdc72e85457c0956ce930795b53df2d319f6ecca050dbe0df5", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "21050201022237386247cf0687735c3a1d361a465d2ae29d446822448c6a46aa", "generation_seconds_batch": 21.568640187964775, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.901240587234497, "target_z": 1.6406249720921613, "ce": 6.340320587158203, "genuineness": 4.557555198669434, "identity": 0.25227707624435425, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/bb621bc9f16f14fdc72e85457c0956ce930795b53df2d319f6ecca050dbe0df5.mp3" }, { "id": "emo_Amusement-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-1", "key": "bb8c57ab52e6b6b638a6c57c19e7732dd7d4b1be0c78dfcdf4cde25e898e52bf", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "bb2225e531f8a5651408d44e20b6e4a2f50939c41c6c88559c10a57b4a81bcd0", "generation_seconds_batch": 24.472374593024142, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.823124408721924, "target_z": 2.7031249291570245, "ce": 6.173524379730225, "genuineness": 4.457139015197754, "identity": 0.6838788986206055, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/bb8c57ab52e6b6b638a6c57c19e7732dd7d4b1be0c78dfcdf4cde25e898e52bf.mp3" }, { "id": "emo_Amusement-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-0", "key": "bb960324f880b712d8598c8dd8f8fc7e9c369363150007358ebf56173aaa6556", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "66049110e8ae264665d8a28324da44e5bb11fac770dd06015edfd2d1f3d26453", "generation_seconds_batch": 18.306890400941484, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9893618822097778, "target_z": 1.7421875225409467, "ce": 6.006728172302246, "genuineness": 4.149612903594971, "identity": 0.6807578802108765, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/bb960324f880b712d8598c8dd8f8fc7e9c369363150007358ebf56173aaa6556.mp3" }, { "id": "emo_Amusement-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-0", "key": "bc1bdc0b743ed8ebba27977b41ee6005fd42528ea60cb2476307b3ab56223e2b", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The door is still open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "c8ab823615d6b3893033721bcc1ba72576e972ae1c979efc0aed41c104f33754", "generation_seconds_batch": 22.576626166002825, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.118154525756836, "target_z": 1.890625075136489, "ce": 6.221180438995361, "genuineness": 4.168440818786621, "identity": 0.1622498780488968, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/bc1bdc0b743ed8ebba27977b41ee6005fd42528ea60cb2476307b3ab56223e2b.mp3" }, { "id": "emo_Amusement-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-0", "key": "bc79cb322421da538bdf034f68311863f24dd333cff81d57166c66df9290d9cc", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De deur staat nog open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "1200ac65ddb5ca479add1c8d6d6e672688bdab6830650534a50bd72be472bd5c", "generation_seconds_batch": 27.296263516996987, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1756093502044678, "target_z": 3.1093748561672925, "ce": 5.959072113037109, "genuineness": 4.068024158477783, "identity": 0.3131076693534851, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/bc79cb322421da538bdf034f68311863f24dd333cff81d57166c66df9290d9cc.mp3" }, { "id": "emo_Amusement-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-1", "key": "bc9787c83a68b72efa15ec8b51fec5b19031c4cb248907cb1cf88c202261909c", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "56525d42916f8cc0923ac4baf8883998f4c0353da36a36003f47466d0ffa5863", "generation_seconds_batch": 16.769443109980784, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5113108158111572, "target_z": 2.3437500042935135, "ce": 6.2767791748046875, "genuineness": 3.6789097785949707, "identity": 0.48838239908218384, "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_Amusement/bc9787c83a68b72efa15ec8b51fec5b19031c4cb248907cb1cf88c202261909c.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": "bca5198a9265236d482cf53b445aab243435a9286d0af635a5ca5ba86add8263", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c94946ae7bf2316c1267ae2ded225590e4784eac999874fd143ac32a6d2f3294", "generation_seconds_batch": 22.17604653595481, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4402986764907837, "target_z": 1.1093749935597295, "ce": 6.340320587158203, "genuineness": 4.3881025314331055, "identity": 0.5405537486076355, "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_Amusement/bca5198a9265236d482cf53b445aab243435a9286d0af635a5ca5ba86add8263.mp3" }, { "id": "emo_Amusement-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-0", "key": "bcd599ea1942cc4429def25fce746fa9ea01a6692e9a5a42b55c1d68b953a7c4", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De deur staat nog open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "03dea62c800a9740fa910506f3b293685435908d7ac241ae9e6f5542e2b12836", "generation_seconds_batch": 22.26219158398453, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6438181400299072, "target_z": 0.19140624731655395, "ce": 5.911416053771973, "genuineness": 4.419482707977295, "identity": 0.5632669925689697, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/bcd599ea1942cc4429def25fce746fa9ea01a6692e9a5a42b55c1d68b953a7c4.mp3" }, { "id": "emo_Amusement-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-0", "key": "bce152e23ad78154414d46a54d9823ad41b312f8e235feeed1024ba292580411", "bucket": "emo_Amusement", "phase": "wording", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De deur staat nog open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "d1bd22cdd34358c37150d4616f94333b42115ed773710d0d5666ac829131bb66", "generation_seconds_batch": 17.25774650007952, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.358955979347229, "target_z": 1.015624989266216, "ce": 5.974957466125488, "genuineness": 4.369274139404297, "identity": 0.7387353181838989, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/bce152e23ad78154414d46a54d9823ad41b312f8e235feeed1024ba292580411.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": "bceed9e0e981704cd0fce3c88b4de54c48ea25440d1d30efc32469bccf922b47", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The road turns left behind the bridge.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a897a77049fd947dcb9fb0c3346d01f062dd4a75829e6fd2637e8a440e91e1db", "generation_seconds_batch": 21.13697203202173, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9793567657470703, "target_z": 0.5781250150272979, "ce": 6.340320587158203, "genuineness": 3.948779582977295, "identity": 0.32908159494400024, "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_Amusement/bceed9e0e981704cd0fce3c88b4de54c48ea25440d1d30efc32469bccf922b47.mp3" }, { "id": "emo_Amusement-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-1", "key": "bcfcadd615edb7cf6d9038d906325a562ebc565330993f13df5666cd0732894f", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "19899925157874dc2e186331d890ac835c989a6ffe67105da6eefb04629bfa02", "generation_seconds_batch": 23.919913090066984, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.297948956489563, "target_z": 0.9453124860460806, "ce": 6.141753673553467, "genuineness": 4.21237325668335, "identity": 0.6344320178031921, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/bcfcadd615edb7cf6d9038d906325a562ebc565330993f13df5666cd0732894f.mp3" }, { "id": "emo_Amusement-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-0", "key": "bd8777b3b1b889538c8ef37813ae1d45319ce0a4bddbb775703065870c1f5af0", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De deur staat nog open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "b1a949b01b562d0162b5ade90ff68ec4ae70ef610f884118576b1aab266ea539", "generation_seconds_batch": 23.96907814196311, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.7043368816375732, "target_z": 3.718749884075131, "ce": 5.959072113037109, "genuineness": 4.174716949462891, "identity": 0.2839990556240082, "hypothesis": "De deur staat nog open! Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/bd8777b3b1b889538c8ef37813ae1d45319ce0a4bddbb775703065870c1f5af0.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": "bd8d1f69205a4b6fde8dcf851053d63751f357ae9ec84b5d235fe9503d489746", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b0a541693a5eb9b02a3d812cc9f739bd297721aa14cca7504aac7ddd9178335c", "generation_seconds_batch": 19.976431137067266, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1113758087158203, "target_z": 1.88281239158878, "ce": 6.268836498260498, "genuineness": 4.494794845581055, "identity": 0.3505609929561615, "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_Amusement/bd8d1f69205a4b6fde8dcf851053d63751f357ae9ec84b5d235fe9503d489746.mp3" }, { "id": "emo_Amusement-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-1", "key": "be12982e8a345e2706a046c9c5bb29a9322fae8ad1763db39337e7d189f3ef82", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "b5ba8f4b5de3e010f4a14df32f7386ae5785f75bf1da4f1d4e33841aaff74f4a", "generation_seconds_batch": 21.94911443197634, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0264811515808105, "target_z": 2.9374999398908086, "ce": 5.95112943649292, "genuineness": 3.998987913131714, "identity": 0.3369935154914856, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/be12982e8a345e2706a046c9c5bb29a9322fae8ad1763db39337e7d189f3ef82.mp3" }, { "id": "emo_Amusement-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-0", "key": "be4750e41f208c57e767b471a2ab7033a1fbf088acdc9868060029e6051a9393", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The door is still open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "8e5d1900773eb4e3cf677ac4c9513294d5bb22e4fbc619cbb0f70e944481fe2f", "generation_seconds_batch": 23.947383363032714, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5148628950119019, "target_z": 1.1953125890904084, "ce": 6.348263263702393, "genuineness": 4.093128204345703, "identity": 0.14587640762329102, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/be4750e41f208c57e767b471a2ab7033a1fbf088acdc9868060029e6051a9393.mp3" }, { "id": "emo_Amusement-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-1", "key": "be841502d0ad266f3fd3f3d296a14136b2f0a8ebb151b1d5b1e195f1129d6a2e", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "c4c052f74c6f93b4d13c7701439266e23358a78feae8421461dc4df99e747e6a", "generation_seconds_batch": 23.01811925007496, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6436554193496704, "target_z": 1.3437500042935138, "ce": 6.268836498260498, "genuineness": 4.469690799713135, "identity": 0.7753475308418274, "hypothesis": "J'ai trouvé la 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_Amusement/be841502d0ad266f3fd3f3d296a14136b2f0a8ebb151b1d5b1e195f1129d6a2e.mp3" }, { "id": "emo_Amusement-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-1", "key": "bf5521e4f4bbb1f066a4af14924b96ec747d7b657e4582bc5e769a84f9a70bdf", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "400e879af338617691c6c130d16c773eb47527f3100f2d08bef3a34bacfa46ba", "generation_seconds_batch": 23.51464685704559, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3350682258605957, "target_z": 2.140624903395943, "ce": 6.054384231567383, "genuineness": 3.7165660858154297, "identity": 0.4038921296596527, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/bf5521e4f4bbb1f066a4af14924b96ec747d7b657e4582bc5e769a84f9a70bdf.mp3" }, { "id": "emo_Amusement-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-1", "key": "bf5635d5fcdee39fc1ef37ecc269f799afc6b818a1e8e9a94669b9a2fef77aa0", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "c6beb87c2c6f09c75728040d0aecc35b5a7b461626788709e1299e5c8869c65f", "generation_seconds_batch": 23.216642514104024, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.728224515914917, "target_z": 2.5937498325529673, "ce": 6.054384231567383, "genuineness": 4.2374773025512695, "identity": 0.3583669364452362, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/bf5635d5fcdee39fc1ef37ecc269f799afc6b818a1e8e9a94669b9a2fef77aa0.mp3" }, { "id": "emo_Amusement-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-0", "key": "bf8ad9d70e7d432b6ae5c965f37b8f7dfce8966090224640cb6105638eb70eb8", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De deur staat nog open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "80295ff691c4f603ef12e4b4f82e1eeb97bbad2410d91f3b7c81e79eb7f05c23", "generation_seconds_batch": 16.761026681982912, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.606210470199585, "target_z": 2.4531248261126968, "ce": 5.816103935241699, "genuineness": 4.306513786315918, "identity": 0.15876741707324982, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/bf8ad9d70e7d432b6ae5c965f37b8f7dfce8966090224640cb6105638eb70eb8.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": "bfa7e96a156d0c7ed3d5b50362eaf4f84eff39e8f3357cf4c2fa5e121f1bdce7", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "c3a800a8b494ce8ab03acfd5bfc9339da03b033ffa8963db998c627f48db8253", "generation_seconds_batch": 20.139344363007694, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.236941933631897, "target_z": 0.8749999828259454, "ce": 6.221180438995361, "genuineness": 4.193545341491699, "identity": 0.6657339930534363, "hypothesis": "Quelqu'un a déplacé la petite chaise bleue. Elle était ici, près de la grande bibliothèque. Nous la remettrons après le déjeuner.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/bfa7e96a156d0c7ed3d5b50362eaf4f84eff39e8f3357cf4c2fa5e121f1bdce7.mp3" }, { "id": "emo_Amusement-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-1", "key": "c06569df004abcbbbbfeeda2dfcff2f754811ab98998707bb033a2cb0136ea7e", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I found the little box.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It was beside the old window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "0c42bcf53c64984c818dda603ad72bbd43aaeb90a01a22213f093ca9cde3f68e", "generation_seconds_batch": 25.480482404935174, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.08070969581604, "target_z": 3.0000000343481092, "ce": 6.086154937744141, "genuineness": 3.835810661315918, "identity": 0.2772209644317627, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/c06569df004abcbbbbfeeda2dfcff2f754811ab98998707bb033a2cb0136ea7e.mp3" }, { "id": "emo_Amusement-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-1", "key": "c0cbf370845e7cb7317b75803d2bd8094eac5ece2f2aabc219e8c8e6d1f43320", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "e07c019be92cc086f2964f27fb9d275cc5de45818c8fa852289d39a0f9db85b1", "generation_seconds_batch": 16.57659907999914, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7114410400390625, "target_z": 1.4218750536689209, "ce": 6.1894097328186035, "genuineness": 4.356721878051758, "identity": 0.6386896371841431, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/c0cbf370845e7cb7317b75803d2bd8094eac5ece2f2aabc219e8c8e6d1f43320.mp3" }, { "id": "emo_Amusement-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-1", "key": "c14649ea05a74b16861627376ea769ef390550ff7d5ae68dd18ebb75840d51cb", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "bf2268c55bba8a02a623e0895cfe3893f8f22d4f8e2635b80f626bd678120aa8", "generation_seconds_batch": 22.532279031933285, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5248677730560303, "target_z": 2.3593748218191832, "ce": 6.006728172302246, "genuineness": 3.9801597595214844, "identity": 0.616051435470581, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/c14649ea05a74b16861627376ea769ef390550ff7d5ae68dd18ebb75840d51cb.mp3" }, { "id": "emo_Amusement-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-0", "key": "c184a0e825a2fe7829a41175bd1ab5166f005bb65c487effb1f5f0fe5574c1de", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The door is still open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "065cb80673a1f9d88963363dd1521429fbf24f84b04a08ac2cd944970623647d", "generation_seconds_batch": 23.88221506390255, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5013056993484497, "target_z": 1.1796874967798647, "ce": 6.292664527893066, "genuineness": 4.005263805389404, "identity": 0.20245403051376343, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/c184a0e825a2fe7829a41175bd1ab5166f005bb65c487effb1f5f0fe5574c1de.mp3" }, { "id": "emo_Amusement-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-0", "key": "c1b6c3e7b1b2df6d5fbdc45527101f919a2ee7d9e5d3abf1dd9406529bcf06a7", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De deur staat nog open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d91a1509c596ce90cb1833b775fa5558f13107c32e0185af812f92cad0598e2f", "generation_seconds_batch": 17.533783124992624, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7114410400390625, "target_z": 1.4218750536689209, "ce": 6.1020402908325195, "genuineness": 4.2751336097717285, "identity": 0.7373771071434021, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/c1b6c3e7b1b2df6d5fbdc45527101f919a2ee7d9e5d3abf1dd9406529bcf06a7.mp3" }, { "id": "emo_Amusement-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-1", "key": "c1c00584b079b23acf7ce75ecff6f901ba12c6e102690468ea51966b85756a88", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "541df551223d684bd60c6fe41d768a2162e230a6e87e8a7caedefb3f1484f2e1", "generation_seconds_batch": 17.77649029402528, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6978839635849, "target_z": 1.4062500987508142, "ce": 6.054384231567383, "genuineness": 4.381826400756836, "identity": 0.5840131640434265, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/c1c00584b079b23acf7ce75ecff6f901ba12c6e102690468ea51966b85756a88.mp3" }, { "id": "emo_Amusement-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-1", "key": "c209a2c88aaf9aa0acc08b45678941a6ce82d4fffdee7c7ac99783894aafeb2f", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "485d8f668bfc70e92c09840c1fed8ea9e4351b7d2cdb4d923ac4f1ca462a00ed", "generation_seconds_batch": 23.57856297097169, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.118154525756836, "target_z": 1.890625075136489, "ce": 5.935244083404541, "genuineness": 3.7793264389038086, "identity": 0.2189655601978302, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/c209a2c88aaf9aa0acc08b45678941a6ce82d4fffdee7c7ac99783894aafeb2f.mp3" }, { "id": "emo_Amusement-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-0", "key": "c2504c553939c27c5e0d98fe4c3517bb23338834b08a6d3b39426d1f09c7338f", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De deur staat nog open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "320103b9c30ac3a6b798a18f47020f2dd90d8cf71da7cb1069e004055436b020", "generation_seconds_batch": 16.75292774301488, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8095672130584717, "target_z": 2.687499836846481, "ce": 5.998785495758057, "genuineness": 4.036643981933594, "identity": 0.366338312625885, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/c2504c553939c27c5e0d98fe4c3517bb23338834b08a6d3b39426d1f09c7338f.mp3" }, { "id": "emo_Amusement-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-0", "key": "c250d6690a14c6ddb7e2a6e635f1cd307df1c79b8e4a6a093ed664da362d3c99", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De deur staat nog open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "439af651ed26551b4ecf7bd1dc62882241bff23fb169e87667d4f3da12593481", "generation_seconds_batch": 18.029827318969183, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7590535879135132, "target_z": 0.3242187076015526, "ce": 6.078212261199951, "genuineness": 4.218649387359619, "identity": 0.7144577503204346, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/c250d6690a14c6ddb7e2a6e635f1cd307df1c79b8e4a6a093ed664da362d3c99.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": "c2783917d5b278b213143556d43948ef1ca34625bbbf3b3d8184e342f304a549", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2ea7463cdffaea4ac3e0099e240a1fe05f39daa1f6d96c286bc4e765a28c5336", "generation_seconds_batch": 19.032322156010196, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7827786207199097, "target_z": 0.35156255044878554, "ce": 6.284721851348877, "genuineness": 3.9927117824554443, "identity": 0.4422625005245209, "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_Amusement/c2783917d5b278b213143556d43948ef1ca34625bbbf3b3d8184e342f304a549.mp3" }, { "id": "emo_Amusement-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-0", "key": "c2a1c159792146096994caec5468ec45dfa7a64a67b511cbab119c8257cc7f45", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The door is still open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c504ad07140fd22fd69e59d962d2f63ac7dc49e23a39b9b46fc9514713a64d2f", "generation_seconds_batch": 19.045326594030485, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7860051393508911, "target_z": 1.5078125118071626, "ce": 6.213237762451172, "genuineness": 3.886019229888916, "identity": 0.45642751455307007, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/c2a1c159792146096994caec5468ec45dfa7a64a67b511cbab119c8257cc7f45.mp3" }, { "id": "emo_Amusement-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-0", "key": "c2cc7f0074cd33f2b3d1210394d005874576a3a8e393744aac5aa59207b267e0", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The door is still open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "7d5fe3ea9479917dfdafd03eebc0806d2768f78747d309e86237b55491043721", "generation_seconds_batch": 23.580510433996096, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4299681186676025, "target_z": 2.25, "ce": 6.268836498260498, "genuineness": 3.6663577556610107, "identity": 0.2988583445549011, "hypothesis": "The door's still open. I put your code on the chair. Tell me when you are ready.", "wer": 0.16666666666666666, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/c2cc7f0074cd33f2b3d1210394d005874576a3a8e393744aac5aa59207b267e0.mp3" }, { "id": "emo_Amusement-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-0", "key": "c2f516dc4f1fd876ec6383d986692e2ecfcdd080759408797a2edc0ca172a88c", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The door is still open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "8b8ce4dd933e8224a977326d5586688452081bffa6287a1aef823ae913e35816", "generation_seconds_batch": 28.21448022790719, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.592653512954712, "target_z": 2.4375000085870275, "ce": 6.1894097328186035, "genuineness": 3.653805732727051, "identity": 0.28713154792785645, "hypothesis": "The door's still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.1111111111111111, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/c2f516dc4f1fd876ec6383d986692e2ecfcdd080759408797a2edc0ca172a88c.mp3" }, { "id": "emo_Amusement-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-0", "key": "c2f6a2c1d4f10c4fbc090ba1b8cdf5b8303f195ca8023aaeec8c4119d70ac4a0", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The door is still open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "55aa36e7739d72b0309a0a54810d37ace8560b6c1a8ab1cf47bd3365014c085f", "generation_seconds_batch": 23.288646325003356, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5113108158111572, "target_z": 2.3437500042935135, "ce": 6.046441555023193, "genuineness": 3.578493118286133, "identity": 0.34365564584732056, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/c2f6a2c1d4f10c4fbc090ba1b8cdf5b8303f195ca8023aaeec8c4119d70ac4a0.mp3" }, { "id": "emo_Amusement-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-0", "key": "c37f3644da12785dd903488873ee6c61596df7870cb17a2973c7ae50465ec75c", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "286d16374f9ad3f36148a279b83377e55c1d26f4b2ce6f3d18ffb6da247120ff", "generation_seconds_batch": 23.803831085911952, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4028539657592773, "target_z": 2.218750090163787, "ce": 6.173524379730225, "genuineness": 4.18099308013916, "identity": 0.5427640080451965, "hypothesis": "La porte est encore ouvre. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/c37f3644da12785dd903488873ee6c61596df7870cb17a2973c7ae50465ec75c.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_Amusement", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": "ee29309ef2d829869a4be213bb073e4cad9cc653d815b4142c5959a762be2ef3", "generation_seconds_batch": 17.238110812031664, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5033748745918274, "target_z": 0.029540988354479634, "ce": 6.062326908111572, "genuineness": 4.65797233581543, "identity": 0.660730242729187, "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_Amusement/c3977db0634952a7f9e4083e6135fbbc87199d34c7cb8c3338515d9ae38c18f4.mp3" }, { "id": "emo_Amusement-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-0", "key": "c41d83cb461fb2c1405a108e8f0dfd8763a82180950059889d256b646f871372", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e0f6b79e6b864e065f1f6a7e33b236256ccf56f2e9d6b11df8c416f423d27254", "generation_seconds_batch": 21.838790362002328, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9893618822097778, "target_z": 1.7421875225409467, "ce": 6.133810997009277, "genuineness": 4.262581825256348, "identity": 0.6473802328109741, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/c41d83cb461fb2c1405a108e8f0dfd8763a82180950059889d256b646f871372.mp3" }, { "id": "emo_Amusement-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-1", "key": "c43b39573a72e626034ff6ba41467b86e65584b0680cc7a60f85cb216ac68487", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "52122d084387e97fc1e08d18cea0a9fa9e386dddbdcb311faa7057fc144003b1", "generation_seconds_batch": 22.95580889005214, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6978839635849, "target_z": 1.4062500987508142, "ce": 6.141753673553467, "genuineness": 4.055472373962402, "identity": 0.5691459774971008, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/c43b39573a72e626034ff6ba41467b86e65584b0680cc7a60f85cb216ac68487.mp3" }, { "id": "emo_Amusement-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-0", "key": "c44adf02746d4fd86cafad25ad6226106479e781dd37c1a9e0cdbaa10f819f46", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De deur staat nog open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "ba37dc9912c1da7cf8d53582c16d963700707a233e9eb32453b90eb6b3bfeed4", "generation_seconds_batch": 21.340378936962225, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1078238487243652, "target_z": 3.0312499441843226, "ce": 6.054384231567383, "genuineness": 4.105680465698242, "identity": 0.5616715550422668, "hypothesis": "De deur staat nog open? Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/c44adf02746d4fd86cafad25ad6226106479e781dd37c1a9e0cdbaa10f819f46.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": "c4726678637fe49d10de8e439e83bdb994d9d51dd43ddd40a19deba62c302509", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Someone moved the little blue chair.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "744fcf9ba2f562bfd933756cbff8202f7458284e55e8935874020311e9fb2866", "generation_seconds_batch": 20.19552803901024, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5148628950119019, "target_z": 1.1953125890904084, "ce": 6.4515180587768555, "genuineness": 4.444586753845215, "identity": 0.40557944774627686, "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_Amusement/c4726678637fe49d10de8e439e83bdb994d9d51dd43ddd40a19deba62c302509.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_Amusement", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": "45532f7965a42e231fececf01dc8d8c98f2c2cc69d585a7526cc49f13b6cc3d3", "generation_seconds_batch": 17.46489887998905, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8963193893432617, "target_z": 0.4824218398468569, "ce": 6.229123115539551, "genuineness": 4.406930446624756, "identity": 0.5462254285812378, "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_Amusement/c493619abd8899c9b3ce96f2a00a6bcdd900e874ef21436707b986365a8437ee.mp3" }, { "id": "emo_Amusement-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-0", "key": "c51ee493d3181c5fcb4204d50d99cd63a8ee2aeb9bd0cf64eaf6a34d4503912d", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The door is still open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "177969855a4bc8fde0c7b8caeff3f4c7506c5b734a822c385f81c46ecc160337", "generation_seconds_batch": 23.295016126008704, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0164761543273926, "target_z": 1.773437569769597, "ce": 6.125868320465088, "genuineness": 3.9048471450805664, "identity": 0.3820491433143616, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/c51ee493d3181c5fcb4204d50d99cd63a8ee2aeb9bd0cf64eaf6a34d4503912d.mp3" }, { "id": "emo_Amusement-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-0", "key": "c55795d783071aca68dfb07efe091100b2380b5b419ee239b73da2886ade68e3", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "7e6066f8f64480753f319d31a7f20c1ca4f94ff83d8ee2abc2a04023437867ff", "generation_seconds_batch": 22.412649714038707, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2877811193466187, "target_z": 0.9335937355093914, "ce": 6.173524379730225, "genuineness": 4.482243061065674, "identity": 0.5517345070838928, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/c55795d783071aca68dfb07efe091100b2380b5b419ee239b73da2886ade68e3.mp3" }, { "id": "emo_Amusement-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-1", "key": "c5ee289133e74aad745ecf5f9d730ab4383b869a3a70e9637416f689dec49a42", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9d538d36bcbbac7f8dab23b25415c5f87d3abad44218db416fe95469b4cd1a69", "generation_seconds_batch": 21.879918935941532, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9147977828979492, "target_z": 1.656250064402705, "ce": 6.459460258483887, "genuineness": 4.049196243286133, "identity": 0.44123944640159607, "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_Amusement/c5ee289133e74aad745ecf5f9d730ab4383b869a3a70e9637416f689dec49a42.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": "c617865535a4e13c8feb4666ee5c71944ad9c4b0877fc9bbdd1a2336ca6fbb96", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Your message arrived after I had left.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ac2059ca239aee0a744085d3d680dafb0f086aeae0c8298b294eb386bb0c5143", "generation_seconds_batch": 24.785941154928878, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.226611375808716, "target_z": 2.015624989266216, "ce": 6.340320587158203, "genuineness": 4.293961524963379, "identity": 0.5010308027267456, "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_Amusement/c617865535a4e13c8feb4666ee5c71944ad9c4b0877fc9bbdd1a2336ca6fbb96.mp3" }, { "id": "emo_Amusement-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-1", "key": "c63d7c39efaf3c1f66a2a8e7cd4f44e8e413a6806cf968b8ba18f7ec4e98bb86", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "2914c9b4ad5aaa7505b3675cc759f7326d4ab2cb7987e72249b45796dd90041b", "generation_seconds_batch": 22.575771374977194, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.023254632949829, "target_z": 1.7812499785324316, "ce": 6.197352409362793, "genuineness": 4.356721878051758, "identity": 0.6154894232749939, "hypothesis": "J'ai trouvé la 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_Amusement/c63d7c39efaf3c1f66a2a8e7cd4f44e8e413a6806cf968b8ba18f7ec4e98bb86.mp3" }, { "id": "emo_Amusement-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-0", "key": "c67a8d85b8d88fbf5ef833580d9ab018d224763f82110f792a34c9241a0f98be", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "6fef21ed832cf52367fe07742951d42f9302d6adb085b8c24a06ccd26d3ca626", "generation_seconds_batch": 24.221248122048564, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.724998116493225, "target_z": 1.4375000085870273, "ce": 6.006728172302246, "genuineness": 4.042920112609863, "identity": 0.5254392623901367, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/c67a8d85b8d88fbf5ef833580d9ab018d224763f82110f792a34c9241a0f98be.mp3" }, { "id": "emo_Amusement-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-0", "key": "c72e67a53ef46770023d639e6d7f0e801a5c600bc05d9dd90f00059007ed9e20", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "31a34b91d1e4c9343b114f0a25413f5820283c5cb4e479b26ae4a496959451b0", "generation_seconds_batch": 23.440377825987525, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3079540729522705, "target_z": 2.1093749935597295, "ce": 5.605623245239258, "genuineness": 3.6475296020507812, "identity": 0.5072593092918396, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/c72e67a53ef46770023d639e6d7f0e801a5c600bc05d9dd90f00059007ed9e20.mp3" }, { "id": "emo_Amusement-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-1", "key": "c74cb1e0e7cf570d2be49b6fe941825b4cf7ef937c94cdd761a7e28510deb935", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "b016f4c2c2c163a2d172a92a4e87189cb6683fe1e7544569b9905c1e7d9ed6cc", "generation_seconds_batch": 23.919913090066984, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7995622158050537, "target_z": 1.523437466725269, "ce": 6.1894097328186035, "genuineness": 4.607763767242432, "identity": 0.640978217124939, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/c74cb1e0e7cf570d2be49b6fe941825b4cf7ef937c94cdd761a7e28510deb935.mp3" }, { "id": "emo_Amusement-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-1", "key": "c816971eea7d440c35ee6518056da7956956ed5b1474a2aabac330bc35937fa0", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I found the little box.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It was beside the old window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "2cb10288c4f4e198076203c24fe90ff4b15375401d1850970af2ad13d51f4084", "generation_seconds_batch": 23.26608707604464, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.945138454437256, "target_z": 2.843749935597295, "ce": 6.324435234069824, "genuineness": 3.8420867919921875, "identity": 0.20932164788246155, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/c816971eea7d440c35ee6518056da7956956ed5b1474a2aabac330bc35937fa0.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_Amusement", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": "8f53ddebaf503fc95b8cbff1f20cc561d2ea7c09d00dcbd5763dc9faaa74c164", "generation_seconds_batch": 17.87232257204596, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4335200786590576, "target_z": 1.1015624474044576, "ce": 6.252951145172119, "genuineness": 4.394378662109375, "identity": 0.6545783281326294, "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_Amusement/c82131bfaf89850d394bf3a21117deb94436b65306054c3e1cbac0c65e2f913d.mp3" }, { "id": "emo_Amusement-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-0", "key": "c84db12ebfa86dec5bd2dbb0e5a1ec530405c7a0838a60c9fa48bf89c405e916", "bucket": "emo_Amusement", "phase": "wording", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "d685eea5f8b781d969e871211b35cb53610f600d44498004fdd247b30afa7f01", "generation_seconds_batch": 17.71025672298856, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3928487300872803, "target_z": 1.0546874452577009, "ce": 6.046441555023193, "genuineness": 3.8295347690582275, "identity": 0.5840667486190796, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/c84db12ebfa86dec5bd2dbb0e5a1ec530405c7a0838a60c9fa48bf89c405e916.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_Amusement", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": "f337411b5db0112bb68ad0a1428b16ee8b0bbbb77b715810437c06f4c0b362bc", "generation_seconds_batch": 17.503765247995034, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4269042909145355, "target_z": -0.05859375268344604, "ce": 6.292664527893066, "genuineness": 4.532451152801514, "identity": 0.3899560570716858, "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_Amusement/c8907269f81c0a33f09ba3b9d9f76b6acb2a8250e6881dbc11786cea01719e9d.mp3" }, { "id": "emo_Amusement-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-1", "key": "c8b8cc990d595d0bb355e86fe845ddc0b47ca955bc0116d5b132c4b95c874004", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I found the little box.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It was beside the old window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "621bef7c5a82c07de25175b1098ec8e47f16bb27eefb2c36f1135ba968156965", "generation_seconds_batch": 23.903421266004443, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8673478364944458, "target_z": 1.6015625161006761, "ce": 6.356205940246582, "genuineness": 4.281409740447998, "identity": 0.36427149176597595, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/c8b8cc990d595d0bb355e86fe845ddc0b47ca955bc0116d5b132c4b95c874004.mp3" }, { "id": "emo_Amusement-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-0", "key": "c8d7b8cd43f7bcab93a5ac40c83a4cffecf4b577505da73f3142f7a43362beaa", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De deur staat nog open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "de4ac6b4cdf092291b8d4a6f9fd7dbcf9b5fd80b9839b66d24503f0166605819", "generation_seconds_batch": 27.78759699303191, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.850238561630249, "target_z": 2.734374838993238, "ce": 6.109982967376709, "genuineness": 4.15588903427124, "identity": 0.2437496781349182, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/c8d7b8cd43f7bcab93a5ac40c83a4cffecf4b577505da73f3142f7a43362beaa.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": "c9c9cb09be80da9588643088d1d4c3155cff4a89bea2f53f76e44f59836b9e1d", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Someone moved the little blue chair.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3ac85b66154bf0e73462296f7fca58841493e38d42ef0bcd603fa944924ae8a6", "generation_seconds_batch": 18.262527006911114, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0505316257476807, "target_z": 0.6601562687841223, "ce": 6.546830177307129, "genuineness": 4.457139015197754, "identity": 0.3137872815132141, "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_Amusement/c9c9cb09be80da9588643088d1d4c3155cff4a89bea2f53f76e44f59836b9e1d.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": "c9e8746dad025d98df4d2694ccadf84af7fe54cbc2dec44d4d939d184b316829", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fe52622b47750c9cfc03a8af0b2cc444c12a3af70446ec48004c1df9bbaaeb74", "generation_seconds_batch": 18.054332925006747, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0300331115722656, "target_z": 1.7890623872952665, "ce": 6.467403411865234, "genuineness": 4.482243061065674, "identity": 0.7172787189483643, "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_Amusement/c9e8746dad025d98df4d2694ccadf84af7fe54cbc2dec44d4d939d184b316829.mp3" }, { "id": "emo_Amusement-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-0", "key": "c9f3916f9b7bb159fd326494c934cac0ffa3184cb032b9d58847067ada50207c", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De deur staat nog open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "bc7cb9c4f2a55ef9a68538549a0ea62859b89c36fb6dc52c44effb74caee57e2", "generation_seconds_batch": 23.96907814196311, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4028539657592773, "target_z": 2.218750090163787, "ce": 5.597680568695068, "genuineness": 4.149612903594971, "identity": 0.4682707190513611, "hypothesis": "De der staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar, wanneer je klaar bent.", "wer": 0.05263157894736842, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/c9f3916f9b7bb159fd326494c934cac0ffa3184cb032b9d58847067ada50207c.mp3" }, { "id": "emo_Amusement-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-0", "key": "cb0a520acb822f94c973e4490ca77f9d8e3916fa327a332ff67cd3c70ca3fede", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De deur staat nog open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "0ebd8cfd17bb8b054f659340bb577502c07cc89eee22510b22246b653750dc41", "generation_seconds_batch": 24.094824225991033, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.728224515914917, "target_z": 2.5937498325529673, "ce": 6.260893821716309, "genuineness": 4.507347106933594, "identity": 0.6947925090789795, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/cb0a520acb822f94c973e4490ca77f9d8e3916fa327a332ff67cd3c70ca3fede.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": "cb4a2fcea1e42124762b43d9b792c38c7c2329fb5695ca4c0a57f0e76abcb767", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "24f8ecd4a77c3996341a30cc8fd4c5b49b0fe785e5ee03c03e62fd1568e4306f", "generation_seconds_batch": 20.106202461058274, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1115386486053467, "target_z": 0.7304687720042575, "ce": 6.260893821716309, "genuineness": 4.193545341491699, "identity": 0.7567873597145081, "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_Amusement/cb4a2fcea1e42124762b43d9b792c38c7c2329fb5695ca4c0a57f0e76abcb767.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": "cbc2fb9656fb062a61a5a476f0a6ddde0accfd14c71b66085faa4cac5ed83f3c", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7533f9cd5833c5b38dbc7bfd8270aeed7d2d68953c2b8ae95de859ab1757cd4e", "generation_seconds_batch": 17.017023405991495, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0810351371765137, "target_z": 0.6953125203941899, "ce": 6.165581703186035, "genuineness": 4.143336772918701, "identity": 0.811331033706665, "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_Amusement/cbc2fb9656fb062a61a5a476f0a6ddde0accfd14c71b66085faa4cac5ed83f3c.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": "ccae3ab9df26c791027e769ea66700ba0e9642d0ad737fd9b355fdd261a30b69", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f4a286ae2f2686cfa79331cb8b6240e6a2dc2bc15539a0ac6e7e5ae418993af3", "generation_seconds_batch": 21.101786165032536, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9893618822097778, "target_z": 1.7421875225409467, "ce": 6.0305562019348145, "genuineness": 4.281409740447998, "identity": 0.5817598104476929, "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_Amusement/ccae3ab9df26c791027e769ea66700ba0e9642d0ad737fd9b355fdd261a30b69.mp3" }, { "id": "emo_Amusement-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-0", "key": "cd29ae62be7397dee0e4efd7f267a7cffc8eda68c6e8f137a78341099467ed41", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De deur staat nog open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "722adcbd808d4a1cb76b3632cfc92363eb3d4a030df69430db9e2ae1cf22d0af", "generation_seconds_batch": 23.91568974603433, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.433194637298584, "target_z": 3.406249961358377, "ce": 6.062326908111572, "genuineness": 4.394378662109375, "identity": 0.1538057178258896, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/cd29ae62be7397dee0e4efd7f267a7cffc8eda68c6e8f137a78341099467ed41.mp3" }, { "id": "emo_Amusement-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-0", "key": "cd58f8287c7ec4dadebb8878a08ff0fc0335e5a63363c5661cb151cb02c580f8", "bucket": "emo_Amusement", "phase": "wording", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The door is still open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "19d53dafd9e5be9249ccbb74ea4b30e1f135e5557e908185303f20040c306dac", "generation_seconds_batch": 16.333980492083356, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2640562057495117, "target_z": 0.9062500300545956, "ce": 6.260893821716309, "genuineness": 3.936227321624756, "identity": 0.2923387289047241, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/cd58f8287c7ec4dadebb8878a08ff0fc0335e5a63363c5661cb151cb02c580f8.mp3" }, { "id": "emo_Amusement-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-1", "key": "cdab39156f008455df3c99b5c855e0d4b8c080d7efc83ba39a65906191a86d2c", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0e6c2db54e08cdc6ab288298b605a41876fd4508131978736df6c8641d4743bc", "generation_seconds_batch": 21.266844974947162, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1520471572875977, "target_z": 1.9296873937355368, "ce": 6.1020402908325195, "genuineness": 4.068024158477783, "identity": 0.6520216464996338, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana, vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/cdab39156f008455df3c99b5c855e0d4b8c080d7efc83ba39a65906191a86d2c.mp3" }, { "id": "emo_Amusement-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-1", "key": "ce12ae568ffc816144e01d86194b0d8b86fb6e72e85d57abd4acd5695d17d2d7", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "9b83b42ed054968d54824dc877120497d4d470353075efe298428369d7db7b0f", "generation_seconds_batch": 25.56944321701303, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5623127222061157, "target_z": 1.25, "ce": 6.086154937744141, "genuineness": 4.250029563903809, "identity": 0.6773905754089355, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/ce12ae568ffc816144e01d86194b0d8b86fb6e72e85d57abd4acd5695d17d2d7.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": "ce4a2ca8cf1049ca61a77228c0e16950fc67933c22b9269903f75b40f89c2059", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The keys are on the kitchen table.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e8da90a4ecf40caad7ca32b02c593c6630e91fa857a41367dc529e1c3053b6f4", "generation_seconds_batch": 18.586985579924658, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.131711483001709, "target_z": 1.9062498926621585, "ce": 6.435632705688477, "genuineness": 3.9048471450805664, "identity": 0.3494836091995239, "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_Amusement/ce4a2ca8cf1049ca61a77228c0e16950fc67933c22b9269903f75b40f89c2059.mp3" }, { "id": "emo_Amusement-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-1", "key": "ce4bd7df837671b6719c0ab1633c71e765c3751fbd8e1b09ff6b28a20f0228b4", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "2c20bbf2cdd128dc7f47425fdb4b2456058a9459da9c997c6bc3d98b56de3242", "generation_seconds_batch": 26.884755780920386, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1994972229003906, "target_z": 1.9843750794300028, "ce": 6.078212261199951, "genuineness": 4.174716949462891, "identity": 0.5601599216461182, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/ce4bd7df837671b6719c0ab1633c71e765c3751fbd8e1b09ff6b28a20f0228b4.mp3" }, { "id": "emo_Amusement-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-1", "key": "ce718f415a5f0a9fff236df13293b8ab6836f53da605113d272046fe4d3e3a3f", "bucket": "emo_Amusement", "phase": "wording", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "3af942fd0f17dccce4857d9508e058011cdf75ed9beceb89a9c0484d9028d62d", "generation_seconds_batch": 17.74995131394826, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1723828315734863, "target_z": 1.9531248948089153, "ce": 6.141753673553467, "genuineness": 4.243753433227539, "identity": 0.747154176235199, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/ce718f415a5f0a9fff236df13293b8ab6836f53da605113d272046fe4d3e3a3f.mp3" }, { "id": "emo_Amusement-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-1", "key": "ce7391ef857f17b4a0d0769260d8dcedfb466029a221a4ba454b7043beb036fe", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "92fb724be6e03963ed138a4e8415d202e003b9257e2632a16d1e2942b003a5a1", "generation_seconds_batch": 16.536964047001675, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.3789660930633545, "target_z": 3.3437498669010766, "ce": 5.95112943649292, "genuineness": 4.15588903427124, "identity": 0.5368632674217224, "hypothesis": "Me he 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_Amusement/ce7391ef857f17b4a0d0769260d8dcedfb466029a221a4ba454b7043beb036fe.mp3" }, { "id": "emo_Amusement-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-1", "key": "cea59a2697843ea51c97f43030d36e4524557436c1fa9ccfd3629ae549ea13cb", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I found the little box.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It was beside the old window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "51f2fe958300f86cb93050997af77d200a3a703ceb7c6d946a9cae5fcb9470f1", "generation_seconds_batch": 23.9244308170164, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5519821643829346, "target_z": 2.3906250064402705, "ce": 6.24500846862793, "genuineness": 3.873466968536377, "identity": 0.449375718832016, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/cea59a2697843ea51c97f43030d36e4524557436c1fa9ccfd3629ae549ea13cb.mp3" }, { "id": "emo_Amusement-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-1", "key": "ceef174fd041a73529d8d8efffc188c553aa2f19b419d34469af0c5d3632822d", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7675380cd22a1990e9779a558d554dbb1e12a2a24ef414068df7994832a152cb", "generation_seconds_batch": 19.191239706007764, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7453337907791138, "target_z": 1.4609375096604058, "ce": 6.403861999511719, "genuineness": 3.8044304847717285, "identity": 0.4475218653678894, "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_Amusement/ceef174fd041a73529d8d8efffc188c553aa2f19b419d34469af0c5d3632822d.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": "cf2e9a491550eab94ff5b370286aae4dee15f4e0a5a3cfdf88622ac1c23e5dbb", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "be61dcc810ee56fed65f7441922fc978df88b0324c4c80095ccf183f80acd141", "generation_seconds_batch": 17.04972067498602, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3725130558013916, "target_z": 1.0312499441843224, "ce": 6.483288764953613, "genuineness": 4.344170093536377, "identity": 0.5989124774932861, "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_Amusement/cf2e9a491550eab94ff5b370286aae4dee15f4e0a5a3cfdf88622ac1c23e5dbb.mp3" }, { "id": "emo_Amusement-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-1", "key": "cf3999ec98da61447c333debac523360cea109c17f7427515884fefe085420eb", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "61716297b2104b97ffa95f7111aa6040dd48965669ada3acfe8a4fdc19b42bed", "generation_seconds_batch": 22.95580889005214, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6911053657531738, "target_z": 1.3984375525955424, "ce": 6.1020402908325195, "genuineness": 3.923675537109375, "identity": 0.6797391176223755, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/cf3999ec98da61447c333debac523360cea109c17f7427515884fefe085420eb.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": "cf4774a26c87c6d2b8587d20bf3be2826b8a8cda7d28de48a07f057d43d55d4b", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5b6817b50962821ca2b1faff81a78c73378407b0cc7aaac067753ab931ef339a", "generation_seconds_batch": 15.603356683044694, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7521123886108398, "target_z": 1.4687500558156776, "ce": 6.173524379730225, "genuineness": 3.923675537109375, "identity": 0.7069527506828308, "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_Amusement/cf4774a26c87c6d2b8587d20bf3be2826b8a8cda7d28de48a07f057d43d55d4b.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_Amusement", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": "f889e70f46e8cfb8d02004398e183fdeceba7ca7d80f4db88c5174c766ec5fd0", "generation_seconds_batch": 17.594678697991185, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.46588099002838135, "target_z": -0.013671887075507174, "ce": 6.260893821716309, "genuineness": 4.143336772918701, "identity": 0.5742809772491455, "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_Amusement/cf68e6506caaaad7e7371e72de9d5417fef89211300487ff83acd2484eaab510.mp3" }, { "id": "emo_Amusement-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-1", "key": "d02bcf457d3c17d10775d1ffa47daca6f6c7e2467b392046c913c583aa5ca668", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3e2abc94ab9034571f7c3f4164f84cf0c8a05c410f7bb0d285aa368dd802b963", "generation_seconds_batch": 17.297067906009033, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.253725528717041, "target_z": 2.046874899102429, "ce": 6.419747352600098, "genuineness": 3.9927117824554443, "identity": 0.6283405423164368, "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_Amusement/d02bcf457d3c17d10775d1ffa47daca6f6c7e2467b392046c913c583aa5ca668.mp3" }, { "id": "emo_Amusement-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-0", "key": "d02ee6b25ec7bec95086c53f2673ca657f742b9104e89f6a4de4d052a733a058", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De deur staat nog open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "b79d9ca08d0c840c396abeb8a276c6b4db1a32ee98acae50e14f40a351cfd599", "generation_seconds_batch": 23.507630279986188, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.192718505859375, "target_z": 1.9765623958822938, "ce": 6.181467056274414, "genuineness": 4.306513786315918, "identity": 0.21824835240840912, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/d02ee6b25ec7bec95086c53f2673ca657f742b9104e89f6a4de4d052a733a058.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": "d0a315d5969426a41f057aa0fdb5ae06f5645f792a1a9235cea340e6508884ea", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "61fc7c7270f6470bf8b4068cef3a0f83c1a0391f42426fe4810a671be690bb85", "generation_seconds_batch": 15.110584764974192, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8673478364944458, "target_z": 1.6015625161006761, "ce": 6.395919322967529, "genuineness": 4.15588903427124, "identity": 0.57603919506073, "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_Amusement/d0a315d5969426a41f057aa0fdb5ae06f5645f792a1a9235cea340e6508884ea.mp3" }, { "id": "emo_Amusement-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-1", "key": "d0b9d4943cd38af813fbf1e4eb8f73b1e6dc5bd4f72a6ffdd25850c9d712f33a", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "823bf2028d697e3908bc3b78791534fba714745a3cf5102beb274205ceb30796", "generation_seconds_batch": 25.689211406977847, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7824530601501465, "target_z": 2.656249927010268, "ce": 6.046441555023193, "genuineness": 4.068024158477783, "identity": 0.581513524055481, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/d0b9d4943cd38af813fbf1e4eb8f73b1e6dc5bd4f72a6ffdd25850c9d712f33a.mp3" }, { "id": "emo_Amusement-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-0", "key": "d0d6b8676cf5c45d695f16f3a281d45b8b83c13127c59dd1551f1747c78e994f", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De deur staat nog open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "62ccdb98a42abd3218aa1bc16dff970561d5079b70e09dfd4b9b43fd7509e3a8", "generation_seconds_batch": 16.75292774301488, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6604390144348145, "target_z": 2.5156249205699974, "ce": 5.95112943649292, "genuineness": 4.306513786315918, "identity": 0.17776653170585632, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/d0d6b8676cf5c45d695f16f3a281d45b8b83c13127c59dd1551f1747c78e994f.mp3" }, { "id": "emo_Amusement-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-0", "key": "d11b0a9b20f68c69a4e2f9d1d5520c550e9eb2525adbf82c4558b352170c1282", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "584013f5f5d2a5fcc89f283be3261f2881b4fca0484e401dcbf56e2eb5f3e942", "generation_seconds_batch": 24.22056260309182, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9825832843780518, "target_z": 1.7343749763856748, "ce": 5.792276382446289, "genuineness": 3.6663577556610107, "identity": 0.3547861576080322, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/d11b0a9b20f68c69a4e2f9d1d5520c550e9eb2525adbf82c4558b352170c1282.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_Amusement", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "de99d64521a25cddd16263cf09604da09be3b31af194a486858d854f3cbc7e8e", "generation_seconds_batch": 17.667185041005723, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6709323525428772, "target_z": 0.22265622584898564, "ce": 6.356205940246582, "genuineness": 4.168440818786621, "identity": 0.32446378469467163, "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_Amusement/d11caac31fa3732e2517803823f1b039213fb31e9438619fd83d8b232c894b7d.mp3" }, { "id": "emo_Amusement-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-0", "key": "d1371668dded12d302f4b1de4810bc0be16596021cebe99f4c509d88c4485c96", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "1d7c01cc09bde3ba2af9f11e91220a8dae2e85a9ae9137563211100c8de05528", "generation_seconds_batch": 18.411084512947127, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.267282724380493, "target_z": 2.0624999914129725, "ce": 6.221180438995361, "genuineness": 4.344170093536377, "identity": 0.6790381073951721, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/d1371668dded12d302f4b1de4810bc0be16596021cebe99f4c509d88c4485c96.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": "d194ad881f21efa0cdcb99501d2dcfd96ab10a6551d591f862d885290183d93a", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [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": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "2518779cff43b4bce16561d5ad3a0ca7b1a36729a3c579f6b6c47a8b2c659cd1", "generation_seconds_batch": 18.277612935984507, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5351985692977905, "target_z": 1.2187500901637869, "ce": 6.252951145172119, "genuineness": 4.494794845581055, "identity": 0.6477369070053101, "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_Amusement/d194ad881f21efa0cdcb99501d2dcfd96ab10a6551d591f862d885290183d93a.mp3" }, { "id": "emo_Amusement-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-1", "key": "d1a32efeb198c0da299ff0399dcc154a3f280c42f88c1ee1dba68faa4bd323ff", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6436d01154d866e2fa725765b99938098734274cdb5a9807adc0d7b337193f4a", "generation_seconds_batch": 21.773747760918923, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.850238561630249, "target_z": 2.734374838993238, "ce": 6.213237762451172, "genuineness": 3.911123275756836, "identity": 0.12890611588954926, "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_Amusement/d1a32efeb198c0da299ff0399dcc154a3f280c42f88c1ee1dba68faa4bd323ff.mp3" }, { "id": "emo_Amusement-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-1", "key": "d1d218e9824193aec276154921b53cb22156fff17fed81e69ae1f8d9ad8d4094", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "c7b783da7c8b159afbd4317600d01fb41d8693ccc3428618e1c4a591f90244d4", "generation_seconds_batch": 23.04370944702532, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8909099102020264, "target_z": 2.7812498411399944, "ce": 6.1020402908325195, "genuineness": 4.162164688110352, "identity": 0.6041929125785828, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/d1d218e9824193aec276154921b53cb22156fff17fed81e69ae1f8d9ad8d4094.mp3" }, { "id": "emo_Amusement-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-1", "key": "d1f8748be16cb20819395620e09337cd564d0a5ca787352d987c97cc5605899d", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7a7915c25b89cb0e1db164362560feaabae64fcd57ddd92e519de3ae04b1bc0e", "generation_seconds_batch": 21.356230317032896, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3079540729522705, "target_z": 2.1093749935597295, "ce": 6.3641486167907715, "genuineness": 3.898571252822876, "identity": 0.3369566798210144, "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_Amusement/d1f8748be16cb20819395620e09337cd564d0a5ca787352d987c97cc5605899d.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_Amusement", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": "014a45d786e0f2f2861cc9861cfa6d2098baf4c79f43ba1fc9fe16f0d9a35650", "generation_seconds_batch": 17.153998289024457, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2572776079177856, "target_z": 0.8984374838993238, "ce": 6.348263263702393, "genuineness": 4.507347106933594, "identity": 0.5771773457527161, "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_Amusement/d2319f0ba4d4a13f099c61fd2524d2cd47bb09bca092815ed8a29e7f5b0c527c.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": "d247ba08058b61ff64b3b119c08c3cc4fc95f53eec56777c072a7d52fd126a56", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "0468c32e1d156c31ca02c56fe67b761cbb39688c1d7701ad778d82953f04680f", "generation_seconds_batch": 19.459677346982062, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0503687858581543, "target_z": 1.8124998883686447, "ce": 6.173524379730225, "genuineness": 4.375550270080566, "identity": 0.5794459581375122, "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_Amusement/d247ba08058b61ff64b3b119c08c3cc4fc95f53eec56777c072a7d52fd126a56.mp3" }, { "id": "emo_Amusement-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-1", "key": "d2543946c41396a0c5813172d5638998d1ede300affb0a598059adc729ffa7d5", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "7039b41449ded3ed8c92759fa1632e745adf7c77d8b1b3964018f2f924ae3259", "generation_seconds_batch": 25.973652609973215, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3115060329437256, "target_z": 0.9609374409641871, "ce": 6.1894097328186035, "genuineness": 4.1998209953308105, "identity": 0.600717306137085, "hypothesis": "J'ai trouvé la 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_Amusement/d2543946c41396a0c5813172d5638998d1ede300affb0a598059adc729ffa7d5.mp3" }, { "id": "emo_Amusement-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-0", "key": "d2780b3ec34789085673894033a4179de0299e4831e172052cd730bde67a1375", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ea01a6fbe2c2d727b587ab959d2c12c4ca11cc280ddeaff75ede00fb6d4b8a69", "generation_seconds_batch": 22.025553654995747, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9486905336380005, "target_z": 1.69531252039419, "ce": 6.070269584655762, "genuineness": 4.3881025314331055, "identity": 0.5074931979179382, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/d2780b3ec34789085673894033a4179de0299e4831e172052cd730bde67a1375.mp3" }, { "id": "emo_Amusement-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-0", "key": "d2c518e3ec4db82f5168ce013abdc90dfc6291a0dc83768193f0eb857328a7d2", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "b84793876f3bb79b8b9dd2c84da1df013eb44dba423b1c8f98b3878eede9044f", "generation_seconds_batch": 18.502018918981776, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.16560435295105, "target_z": 1.9453124860460806, "ce": 6.221180438995361, "genuineness": 4.319066047668457, "identity": 0.4506993293762207, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/d2c518e3ec4db82f5168ce013abdc90dfc6291a0dc83768193f0eb857328a7d2.mp3" }, { "id": "emo_Amusement-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-1", "key": "d2daad538504032f87bd49ce4b813923e158a443be86f5d4b9042a80fac0a0a4", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I found the little box.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It was beside the old window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "dec46196dddb633d03ec84385a8c3c369299e32c42e1937666c644002f7463a6", "generation_seconds_batch": 18.355054907035083, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.714667558670044, "target_z": 2.5781250150272976, "ce": 6.308549880981445, "genuineness": 4.042920112609863, "identity": 0.34960442781448364, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/d2daad538504032f87bd49ce4b813923e158a443be86f5d4b9042a80fac0a0a4.mp3" }, { "id": "emo_Amusement-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-0", "key": "d2ec0dbdc471cb327371b3db64d92b5202ee26a3ffc4c118ad3d20ef9174d508", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f56f9ca0f12dc13270b25b046f88a5c1a9cb48677cc29aef6a5d97dabee319cd", "generation_seconds_batch": 18.096876902971417, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9419119358062744, "target_z": 1.687499974238918, "ce": 6.141753673553467, "genuineness": 4.068024158477783, "identity": 0.5552014112472534, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/d2ec0dbdc471cb327371b3db64d92b5202ee26a3ffc4c118ad3d20ef9174d508.mp3" }, { "id": "emo_Amusement-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-0", "key": "d31ddecfa97deaf99f70158bc017f63a98b9b8f095bf68561fc4fec62b571be2", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The door is still open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "0a01bca182f83dbb1bff8fe6e330cdeae63e3f1d498c4d605270535b87c66697", "generation_seconds_batch": 15.641851922031492, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.497753620147705, "target_z": 2.32812491198297, "ce": 6.157639026641846, "genuineness": 3.6914620399475098, "identity": 0.35184571146965027, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/d31ddecfa97deaf99f70158bc017f63a98b9b8f095bf68561fc4fec62b571be2.mp3" }, { "id": "emo_Amusement-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-0", "key": "d37faee09f20490dc85b5fcd76b3f3f34e7c49c967d21801533f1ed3b5544f6d", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "de7a15d6d858635dc1ff2293e2629165a91130a37a2b5f734ccd9e26a63c2385", "generation_seconds_batch": 23.789832510985434, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.21321702003479, "target_z": 0.8476562773711496, "ce": 6.022613525390625, "genuineness": 3.9425034523010254, "identity": 0.5974053144454956, "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_Amusement/d37faee09f20490dc85b5fcd76b3f3f34e7c49c967d21801533f1ed3b5544f6d.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": "d38139c2d5040ecc526d2b1db40bef48cf1663b9a7866e5e6ae3ff238de65b12", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I wrote the number on the envelope.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0873428ecd774f805c7ad596e04388b2d7492c8e2250f21f3ddb2a0aeae8a38e", "generation_seconds_batch": 15.230817312956788, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.480970025062561, "target_z": 1.1562499957064862, "ce": 6.340320587158203, "genuineness": 4.024092197418213, "identity": 0.3460373282432556, "hypothesis": "I wrote the number on the envelope. Write it carefully and check the last two digits. Call me when you have a moment.", "wer": 0.043478260869565216, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/d38139c2d5040ecc526d2b1db40bef48cf1663b9a7866e5e6ae3ff238de65b12.mp3" }, { "id": "emo_Amusement-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-1", "key": "d383fc4842d9d493ea12c8b5dfa76acfe658267d71bd15f3d6a223d6113dcc09", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "c318309e19e2c9675f87947c930e13881549185c529caabaeafbc76629511928", "generation_seconds_batch": 21.800766972941346, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4164109230041504, "target_z": 2.2343749076894563, "ce": 6.09409761428833, "genuineness": 4.18099308013916, "identity": 0.6958774328231812, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/d383fc4842d9d493ea12c8b5dfa76acfe658267d71bd15f3d6a223d6113dcc09.mp3" }, { "id": "emo_Amusement-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-0", "key": "d39e4229c2abbd41f79f9857bad4184c19f46dea42934589d2c7fae792402ec8", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "0ede38dfda453aa005ac4a200369fb5ef01b063cb1cb8c2e50cefa54401a02a8", "generation_seconds_batch": 18.096876902971417, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2943968772888184, "target_z": 2.093749901249186, "ce": 6.181467056274414, "genuineness": 4.105680465698242, "identity": 0.21326804161071777, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/d39e4229c2abbd41f79f9857bad4184c19f46dea42934589d2c7fae792402ec8.mp3" }, { "id": "emo_Amusement-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-1", "key": "d3b9bb6cfde101ecefbb7ad5f3f7b561ae8923131012ef398ab6c59776a8f72e", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "e042874cc3770dbbd530e5f6ccbadca8d41468883d1dabccc5dc13a8b26a24d9", "generation_seconds_batch": 24.693575448007323, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.728224515914917, "target_z": 2.5937498325529673, "ce": 6.157639026641846, "genuineness": 4.344170093536377, "identity": 0.19203707575798035, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/d3b9bb6cfde101ecefbb7ad5f3f7b561ae8923131012ef398ab6c59776a8f72e.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_Amusement", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": "44b098c511f9de78d9496ac7f6d39cf86c98d22371ed2da0d152881d2ab26051", "generation_seconds_batch": 18.116780833923258, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9861353635787964, "target_z": 0.5859375611825697, "ce": 6.149696350097656, "genuineness": 4.7081804275512695, "identity": 0.6517966985702515, "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_Amusement/d3fab0ead1fc9dcf899f59bddb0c9d4b54373ba1829b6dc49f77fc4027ce1740.mp3" }, { "id": "emo_Amusement-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-0", "key": "d48e7b30c0d6f09c4485ceb5b1f84618be51cde21e2333393616c0da5ae731cc", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The door is still open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "4fb43f652b861bf85bcc19c508a0be2156eea33359626000618fae408d4694ef", "generation_seconds_batch": 19.045326594030485, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.009697437286377, "target_z": 1.765624886221888, "ce": 6.197352409362793, "genuineness": 3.603597402572632, "identity": 0.20840170979499817, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/d48e7b30c0d6f09c4485ceb5b1f84618be51cde21e2333393616c0da5ae731cc.mp3" }, { "id": "emo_Amusement-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-0", "key": "d4bb5d2c6d44129eaeea8120138804fdd9acae74007db0269475ca0f6fdf4961", "bucket": "emo_Amusement", "phase": "wording", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "64e477e9b33376e5288b2d2527816a1cb1ba530c2c9018300918f8fbbf3c7576", "generation_seconds_batch": 16.289099897025153, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8605692386627197, "target_z": 1.5937499699454043, "ce": 6.1894097328186035, "genuineness": 4.331617832183838, "identity": 0.46024638414382935, "hypothesis": "Die Tür ist noch offen? Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/d4bb5d2c6d44129eaeea8120138804fdd9acae74007db0269475ca0f6fdf4961.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": "d4c6bacf338a14fe9cec79c8bcf5af248e4955a8b0386946a4ebe0eaa4bcedfb", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e99e7e25b8cacaecc3f34c36b09c9ac2451d960a80be6038373472a6ac775771", "generation_seconds_batch": 17.01973423396703, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6436554193496704, "target_z": 1.3437500042935138, "ce": 6.157639026641846, "genuineness": 4.557555198669434, "identity": 0.6664143800735474, "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_Amusement/d4c6bacf338a14fe9cec79c8bcf5af248e4955a8b0386946a4ebe0eaa4bcedfb.mp3" }, { "id": "emo_Amusement-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-1", "key": "d5b110098aa13cba3c1029c407659eb2b0076659a099a372dd733f992022c0f9", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "a4232acc4eb906175c110c398c17333d99aea686115518ee48653e1f4d60c2cb", "generation_seconds_batch": 21.90396010200493, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.023254632949829, "target_z": 1.7812499785324316, "ce": 6.300607204437256, "genuineness": 4.20609712600708, "identity": 0.568955659866333, "hypothesis": "J'ai trouvé la 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_Amusement/d5b110098aa13cba3c1029c407659eb2b0076659a099a372dd733f992022c0f9.mp3" }, { "id": "emo_Amusement-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-1", "key": "d70ffaf809a8820ce1195d96a47dd375128ff732a7cf5bcd0266f2f9793ef5af", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "c6c1c5191dd6ce8e15841203d9754813aec9e529b63b39e8930e56f2b6448abd", "generation_seconds_batch": 17.67427121894434, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3215112686157227, "target_z": 2.125000085870273, "ce": 6.2767791748046875, "genuineness": 4.243753433227539, "identity": 0.5327008366584778, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/d70ffaf809a8820ce1195d96a47dd375128ff732a7cf5bcd0266f2f9793ef5af.mp3" }, { "id": "emo_Amusement-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-1", "key": "d75402a4cf808a101991cd7de39932f4c384e9e9ae3a6abf7c96fce7afdc7e47", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "d91fb460ccb44c3d6cd43bcfb679924c4c96e19acadd5cb1b86c8864cd90d0ce", "generation_seconds_batch": 16.045714076957665, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2130541801452637, "target_z": 1.999999896955672, "ce": 6.0146708488464355, "genuineness": 4.2249250411987305, "identity": 0.6121494770050049, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/d75402a4cf808a101991cd7de39932f4c384e9e9ae3a6abf7c96fce7afdc7e47.mp3" }, { "id": "emo_Amusement-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-1", "key": "d792599592466062cb0e3ba8280b8c4e71a2899d62f371d359c245109d525590", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1e02eaf7968ed16599432ce1be6fa523210c5365de41672ede5e2ff1c2f7acb2", "generation_seconds_batch": 18.047275956952944, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.240168571472168, "target_z": 2.0312500815767596, "ce": 6.395919322967529, "genuineness": 3.9801597595214844, "identity": 0.5059162378311157, "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_Amusement/d792599592466062cb0e3ba8280b8c4e71a2899d62f371d359c245109d525590.mp3" }, { "id": "emo_Amusement-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-1", "key": "d7edbab6c9e9860a7b8fdbb638347df08d318346cce2a540f45214ff4aca5a91", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "b8dbe7e39e599e6f1bb44d395c786e3fd82a855abe27caa67c998332f5d09b04", "generation_seconds_batch": 23.81260333303362, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3115060329437256, "target_z": 0.9609374409641871, "ce": 6.181467056274414, "genuineness": 4.469690799713135, "identity": 0.44887879490852356, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/d7edbab6c9e9860a7b8fdbb638347df08d318346cce2a540f45214ff4aca5a91.mp3" }, { "id": "emo_Amusement-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-0", "key": "d7f2cf485ddaa4c462749aaf32dd46633e6949f30a0c24e4af54a117f823035d", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "124f3ec2d76ed99284724b40ee795ca97f2f8ab0f01297ac8cb4a4253f41cfc6", "generation_seconds_batch": 26.64550759003032, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5962055921554565, "target_z": 1.2890625933839222, "ce": 5.895530700683594, "genuineness": 4.174716949462891, "identity": 0.48182132840156555, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/d7f2cf485ddaa4c462749aaf32dd46633e6949f30a0c24e4af54a117f823035d.mp3" }, { "id": "emo_Amusement-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-1", "key": "d83ae59853dc63ac6c78f2ebeaeb2a53f0549e041801b64bc5bb843a2d3d2760", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "97120822d79a61aa2b70506646d213c8f07c40ba6d4d69c95741593e097d67f6", "generation_seconds_batch": 18.014813481946476, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3079540729522705, "target_z": 2.1093749935597295, "ce": 5.982900142669678, "genuineness": 4.174716949462891, "identity": 0.38157063722610474, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/d83ae59853dc63ac6c78f2ebeaeb2a53f0549e041801b64bc5bb843a2d3d2760.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": "d86cc2231243c535f1447fa5a6e92d5199ffff76de5f746f61f6ac0afac04f10", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "06369774c64525f4b9f380007af71c8f9b4eb66f4c05c5515426548af58052ce", "generation_seconds_batch": 19.459677346982062, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6739962100982666, "target_z": 2.531250012880541, "ce": 6.284721851348877, "genuineness": 4.118232727050781, "identity": 0.6810857653617859, "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_Amusement/d86cc2231243c535f1447fa5a6e92d5199ffff76de5f746f61f6ac0afac04f10.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": "d8e2e6c4de702c87614e9b6130d441f61513d51efb68733b709b7a2816dbec23", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f0ad21ecac013d0ff9533926faef3beca3c2f02a04f8a04bff228ddfbd716a32", "generation_seconds_batch": 20.196450357092544, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4402986764907837, "target_z": 1.1093749935597295, "ce": 6.205295085906982, "genuineness": 4.545003414154053, "identity": 0.5382511615753174, "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_Amusement/d8e2e6c4de702c87614e9b6130d441f61513d51efb68733b709b7a2816dbec23.mp3" }, { "id": "emo_Amusement-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-0", "key": "d995a11c55c99baa44dbe6051af6f0d0497e063666469e1558ed901f1a49c4a8", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De deur staat nog open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "42ab4bdd70818115bdd62ab7a20db428b17631ba34ed92a15f2623b0c318dff7", "generation_seconds_batch": 18.096010698005557, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4570822715759277, "target_z": 2.281249909836213, "ce": 6.046441555023193, "genuineness": 4.193545341491699, "identity": 0.29263776540756226, "hypothesis": "De deur 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_Amusement/d995a11c55c99baa44dbe6051af6f0d0497e063666469e1558ed901f1a49c4a8.mp3" }, { "id": "emo_Amusement-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-0", "key": "d9d31e62da43b9e871aa1ab5151f08fbd3081b7ff2c102ef4c15317a968ec298", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "f88adec12adb79fe8c0ee9281834e04fcf28262e76b985025af56cddc077d430", "generation_seconds_batch": 23.314232376986183, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9825832843780518, "target_z": 1.7343749763856748, "ce": 6.268836498260498, "genuineness": 4.086852550506592, "identity": 0.7567620873451233, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/d9d31e62da43b9e871aa1ab5151f08fbd3081b7ff2c102ef4c15317a968ec298.mp3" }, { "id": "emo_Amusement-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-0", "key": "d9f2d71c107b04b28bcca956a2532527cd90973236f640b049207d1b5dfb67c4", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De deur staat nog open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "baaeee60a0e4531e2d7580067b92c0571b77b5cf9763a2db5977e930f6fd4e3e", "generation_seconds_batch": 23.507630279986188, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.131711483001709, "target_z": 1.9062498926621585, "ce": 6.109982967376709, "genuineness": 4.356721878051758, "identity": 0.7428621649742126, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/d9f2d71c107b04b28bcca956a2532527cd90973236f640b049207d1b5dfb67c4.mp3" }, { "id": "emo_Amusement-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-0", "key": "da4513ee2e3ced8d34d93decc9536263a77b76785d9ccd630262d8e2e24cbfe9", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "064f8efc4ce1c9c9f8db3f41f13b8e1b9b4bb5f5ff3f3c257bb73acb721a2196", "generation_seconds_batch": 16.829551446950063, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6739962100982666, "target_z": 2.531250012880541, "ce": 5.967014789581299, "genuineness": 4.049196243286133, "identity": 0.4020414352416992, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/da4513ee2e3ced8d34d93decc9536263a77b76785d9ccd630262d8e2e24cbfe9.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": "da5af2ad3d82882ebe8e60e4fca3431f9e87282e2a7c868e1827f461980725ce", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3b5df7eb72e44ed84feed9488f97db075d5f50a2329570ad83a7bc3139f4c6c1", "generation_seconds_batch": 20.120428815949708, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8944621086120605, "target_z": 1.6328125633293264, "ce": 6.133810997009277, "genuineness": 4.362998008728027, "identity": 0.7329315543174744, "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_Amusement/da5af2ad3d82882ebe8e60e4fca3431f9e87282e2a7c868e1827f461980725ce.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_Amusement", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": "b6a5152de86baac4e41d7fbd036416eddc57b443a5aa9a4287713c2a9d125e8f", "generation_seconds_batch": 17.845964765991084, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24218858778476715, "target_z": -0.2714843817086151, "ce": 6.467403411865234, "genuineness": 4.18099308013916, "identity": 0.49491676688194275, "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_Amusement/db192910e9ae67de251fb2a990940eab881f66f627c78b50b638ce61f5a63679.mp3" }, { "id": "emo_Amusement-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-0", "key": "db81c7e7426a0c82ef079a236a14590c5f923cdc802be3df1c060066c83becb6", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "08194a134a5097b90e1382516a423554de0b8466559042b2fc8d9faddb7d295e", "generation_seconds_batch": 23.440377825987525, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5519821643829346, "target_z": 2.3906250064402705, "ce": 5.784333229064941, "genuineness": 3.7416701316833496, "identity": 0.42107295989990234, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/db81c7e7426a0c82ef079a236a14590c5f923cdc802be3df1c060066c83becb6.mp3" }, { "id": "emo_Amusement-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-1", "key": "db8cfd1b1c89bd0e810c8d641e8e48c1f1661545c3347533aa24f08943142279", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "b532be861a8829f10264706b50ace62653ba578edb3ef46ab8d641b99b5edaa8", "generation_seconds_batch": 21.906306438031606, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.118154525756836, "target_z": 1.890625075136489, "ce": 6.252951145172119, "genuineness": 4.507347106933594, "identity": 0.5380882024765015, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/db8cfd1b1c89bd0e810c8d641e8e48c1f1661545c3347533aa24f08943142279.mp3" }, { "id": "emo_Amusement-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-0", "key": "dbad7e083dadb62f51e2679460a92fdf19e96023dc41b2dbee032d5c46ed7455", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "9c68d6822e405278e207ca5981813c3bcb52266d9ef7af5fda87098fa0997f1f", "generation_seconds_batch": 20.42649314389564, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.47063946723938, "target_z": 2.296875002146757, "ce": 5.422942161560059, "genuineness": 3.6851859092712402, "identity": 0.5264451503753662, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/dbad7e083dadb62f51e2679460a92fdf19e96023dc41b2dbee032d5c46ed7455.mp3" }, { "id": "emo_Amusement-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-1", "key": "dc95d353e65428ba1c6122117d89c63b963d883157bd86f6c0fb9f62e5663725", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I found the little box.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It was beside the old window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "b60c5dca273410953666482f6d1bc894856e97d83e67bb3488a0872978f9330e", "generation_seconds_batch": 25.480482404935174, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6875531673431396, "target_z": 2.5468748304062103, "ce": 5.974957466125488, "genuineness": 3.8546390533447266, "identity": 0.40240103006362915, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/dc95d353e65428ba1c6122117d89c63b963d883157bd86f6c0fb9f62e5663725.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": "dcadbd88427e4cfc9b60c5bf25fc271951266d256d4e5f56104f246961ee47cd", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The road turns left behind the bridge.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c44911909462f68022ad339be65a714460e21db4325b570661afdc3bc7b493b6", "generation_seconds_batch": 19.422961750999093, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5133309364318848, "target_z": 0.04101566122652152, "ce": 6.523001670837402, "genuineness": 4.256305694580078, "identity": 0.344632089138031, "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_Amusement/dcadbd88427e4cfc9b60c5bf25fc271951266d256d4e5f56104f246961ee47cd.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": "dcf1eda47d59d08dc781825ddcfc2f9a150884fb749a9f5624288029d4855cce", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ebc8361c569e7916b74632b70bc6f50aef3b3eed91fc180c879739df06c2ce49", "generation_seconds_batch": 20.099594148923643, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7927837371826172, "target_z": 1.5156250579624344, "ce": 6.1894097328186035, "genuineness": 4.557555198669434, "identity": 0.7303215265274048, "hypothesis": "J'écris le numéro sur l'enveloppe, lis le bien et vérifie les deux derniers chiffres. Appelle-moi quand il y aura un moment.", "wer": 0.22727272727272727, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/dcf1eda47d59d08dc781825ddcfc2f9a150884fb749a9f5624288029d4855cce.mp3" }, { "id": "emo_Amusement-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-0", "key": "dcf46701464b3b34693ebcf41cdb220a79af421ba834f243cdafb8260a1dca7f", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "1893f57daf2ad324d3c6cd80d6efebbe4dd4cfe50c56f8c0a9d97752846b7701", "generation_seconds_batch": 18.04508306796197, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.097981572151184, "target_z": 0.714843817086151, "ce": 6.443574905395508, "genuineness": 4.482243061065674, "identity": 0.4518895149230957, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/dcf46701464b3b34693ebcf41cdb220a79af421ba834f243cdafb8260a1dca7f.mp3" }, { "id": "emo_Amusement-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-1", "key": "dd57693b6a9901ebd31563a387b1f3bb946890cf9909be3785e74a156d27a6fa", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "d670cc62b183bb5b91b269350f33e050b2db360fd88bd354837c3c70cc96af2a", "generation_seconds_batch": 24.464732920052484, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1520471572875977, "target_z": 1.9296873937355368, "ce": 6.300607204437256, "genuineness": 3.6663577556610107, "identity": 0.4320136308670044, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/dd57693b6a9901ebd31563a387b1f3bb946890cf9909be3785e74a156d27a6fa.mp3" }, { "id": "emo_Amusement-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-1", "key": "dd78a553ddffa6919c32275fd85211ecbdcf7c4a619c7ec437b3a5a2ad221a6c", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "3f6f99bf811832873b4db039e87663f39b91d86674da23efe9d779e60417801f", "generation_seconds_batch": 21.170096761896275, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9419119358062744, "target_z": 1.687499974238918, "ce": 6.284721851348877, "genuineness": 4.3881025314331055, "identity": 0.7827576398849487, "hypothesis": "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_Amusement/dd78a553ddffa6919c32275fd85211ecbdcf7c4a619c7ec437b3a5a2ad221a6c.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": "ddb9ae6ba108aee5fae1f3291c74351472b370c7f825fe8483d0e3c6a2ba485e", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "05d1b3cc6a328f8af5f27e38e1703eb69790a66030b2eb7e405878e4c82c3ec8", "generation_seconds_batch": 20.43811117298901, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4028539657592773, "target_z": 2.218750090163787, "ce": 6.086154937744141, "genuineness": 4.482243061065674, "identity": 0.6442520618438721, "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_Amusement/ddb9ae6ba108aee5fae1f3291c74351472b370c7f825fe8483d0e3c6a2ba485e.mp3" }, { "id": "emo_Amusement-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-0", "key": "de4af72672d5da094c4690a181ce27b037517522832f3bb26c3f07e1e948d1b3", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De deur staat nog open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "7d96f0e266742b8164191531d7c4be0d2463517c0c017ee495935612e66c0b8f", "generation_seconds_batch": 25.060368446982466, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8198978900909424, "target_z": 1.5468749677986475, "ce": 6.141753673553467, "genuineness": 4.168440818786621, "identity": 0.1980932354927063, "hypothesis": "De deur 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_Amusement/de4af72672d5da094c4690a181ce27b037517522832f3bb26c3f07e1e948d1b3.mp3" }, { "id": "emo_Amusement-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-0", "key": "de70edaf386f7beec7a2e58da9f14e51ef76f6171f5667466962cbe78ba4b075", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The door is still open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "722a8b378e7fa089eb5aefeb211d975d5583bad7fbbb9660dec3c6f2fbeceadc", "generation_seconds_batch": 23.866428078967147, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7553389072418213, "target_z": 2.6250000171740546, "ce": 6.078212261199951, "genuineness": 3.616149425506592, "identity": 0.24271397292613983, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/de70edaf386f7beec7a2e58da9f14e51ef76f6171f5667466962cbe78ba4b075.mp3" }, { "id": "emo_Amusement-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-1", "key": "de9ddf9781897d720248b7e02254b4ef38fd3534fcf6014782735bebc51e89da", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "6860edea166dbe57710fbd1914a2155c7300bb2c2d937e9377d502e24c1bea8f", "generation_seconds_batch": 24.07742852193769, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3318417072296143, "target_z": 0.9843749420375656, "ce": 6.197352409362793, "genuineness": 4.557555198669434, "identity": 0.6605366468429565, "hypothesis": "J'ai trouvé la 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_Amusement/de9ddf9781897d720248b7e02254b4ef38fd3534fcf6014782735bebc51e89da.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": "dea8d6897681ad4591cd07cecf8b2722aa9116d003ca8e954715a4a43b5c3fb4", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The road turns left behind the bridge.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "24958a14bb2b4305443824b797a83989c6ad1f5ab827596cc00bd2bfa21bb6d7", "generation_seconds_batch": 21.13697203202173, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0708673000335693, "target_z": 0.6835937698575006, "ce": 6.356205940246582, "genuineness": 4.049196243286133, "identity": 0.3855777978897095, "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_Amusement/dea8d6897681ad4591cd07cecf8b2722aa9116d003ca8e954715a4a43b5c3fb4.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": "dee3f249c2698339d36fbeadc577fbeb70dbfeba17d6caca27defceb69e56edb", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [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": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "464f2be48f098d089b90854432fdc3a3800f75c53855f4eb3b1f63bf6998d2ec", "generation_seconds_batch": 17.584241957054473, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1723828315734863, "target_z": 1.9531248948089153, "ce": 6.173524379730225, "genuineness": 4.287685871124268, "identity": 0.6162711381912231, "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_Amusement/dee3f249c2698339d36fbeadc577fbeb70dbfeba17d6caca27defceb69e56edb.mp3" }, { "id": "emo_Amusement-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-0", "key": "df37126bbe865cde4a35f955b5c2b678e5f6683a18fec3bbf2917ee2a260a162", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De deur staat nog open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "c1ac09fff0b81c4c9371032ea98a06f55c179990261fc700005fa6ff5b027f43", "generation_seconds_batch": 18.029827318969183, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.253725528717041, "target_z": 2.046874899102429, "ce": 5.982900142669678, "genuineness": 3.9927117824554443, "identity": 0.14283451437950134, "hypothesis": "De deur staat nog open? Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/df37126bbe865cde4a35f955b5c2b678e5f6683a18fec3bbf2917ee2a260a162.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": "df9f2a462714858a0294d66b24a7105549606fea747e2cf8962c7e8c5e9a91cc", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7d5babfc38aade7a139150d2a0855c11436a86af8a70c07bc5660852f05ffa5d", "generation_seconds_batch": 17.211506263003685, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.070704460144043, "target_z": 1.8359373894420232, "ce": 6.141753673553467, "genuineness": 4.162164688110352, "identity": 0.35009515285491943, "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_Amusement/df9f2a462714858a0294d66b24a7105549606fea747e2cf8962c7e8c5e9a91cc.mp3" }, { "id": "emo_Amusement-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-1", "key": "e0713c812f0f895f9646bfef2e0bcc1f4050076af6525e1f3d0acb4a2ad7d851", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "32f9dd15dcf1e8956147b04bf3143f5e6fa8febdc24a8ae15297ba6015a6090b", "generation_seconds_batch": 24.76977893000003, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.497753620147705, "target_z": 2.32812491198297, "ce": 6.284721851348877, "genuineness": 4.18099308013916, "identity": 0.45342251658439636, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/e0713c812f0f895f9646bfef2e0bcc1f4050076af6525e1f3d0acb4a2ad7d851.mp3" }, { "id": "emo_Amusement-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-1", "key": "e09797d5c886fff18a75dbfb7726a20e1deb6ef5a1bf44729508edd52e6199d0", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "5664d343755a4e10c2f521065e66afb380ed8c036553a85904770f48d580534d", "generation_seconds_batch": 23.003820789977908, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2943968772888184, "target_z": 2.093749901249186, "ce": 6.070269584655762, "genuineness": 4.093128204345703, "identity": 0.3145638704299927, "hypothesis": "Ik heb het kleine touwje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/e09797d5c886fff18a75dbfb7726a20e1deb6ef5a1bf44729508edd52e6199d0.mp3" }, { "id": "emo_Amusement-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-0", "key": "e0aec08a90e6ad4721926f432952e5e0230196b118e99872d3d1f74c226291ff", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0fde99fe99980e0c2dbede62a2ed8103fc2e449e108bcf1dda1af5f95bbbbd27", "generation_seconds_batch": 23.280330864945427, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.592653512954712, "target_z": 2.4375000085870275, "ce": 6.252951145172119, "genuineness": 4.049196243286133, "identity": 0.44112125039100647, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/e0aec08a90e6ad4721926f432952e5e0230196b118e99872d3d1f74c226291ff.mp3" }, { "id": "emo_Amusement-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-0", "key": "e0cd850201531671a99e60d7ffc1ea46af5af43c91a33520c2807e4d69471d2a", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "36905ad6c4b0cc47a851320c6d619db26213cdbd3e5392c57e6773eab2e8c07e", "generation_seconds_batch": 21.97039549902547, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3725130558013916, "target_z": 1.0312499441843224, "ce": 6.070269584655762, "genuineness": 3.8671910762786865, "identity": 0.5102466344833374, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/e0cd850201531671a99e60d7ffc1ea46af5af43c91a33520c2807e4d69471d2a.mp3" }, { "id": "emo_Amusement-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-1", "key": "e0d3d5b08cd0ad764d90e009275c8d6ad6301b9d48d76a12a3294ba8e94311d5", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4169046b32414ea6eb5f79f0862dbca7c2b4c8cbbb21a7aef45a102e13b8ea28", "generation_seconds_batch": 23.370527168968692, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5384249687194824, "target_z": 2.374999914129727, "ce": 6.141753673553467, "genuineness": 4.093128204345703, "identity": 0.1780272275209427, "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_Amusement/e0d3d5b08cd0ad764d90e009275c8d6ad6301b9d48d76a12a3294ba8e94311d5.mp3" }, { "id": "emo_Amusement-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-1", "key": "e134358ef02c997e745398878e1b791e9e65ef06f87c1fa12f2f6b258b3f7d84", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I found the little box.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It was beside the old window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "afcc0e5be8ebdd40f4ee55a8aab6d38445fde2a4ab1a9d4e5329f5d57413a333", "generation_seconds_batch": 24.56803324702196, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4164109230041504, "target_z": 2.2343749076894563, "ce": 6.23706579208374, "genuineness": 4.080576419830322, "identity": 0.39342865347862244, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/e134358ef02c997e745398878e1b791e9e65ef06f87c1fa12f2f6b258b3f7d84.mp3" }, { "id": "emo_Amusement-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-0", "key": "e13697cb88cf8581b78c21eea80ae0dfe44c74ae9774b9dc91773afeeb9c9ae7", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The door is still open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "5e3eb151f657c65f7e0576a4c21a52b50d34e260c70a6b076192574cc50e37cc", "generation_seconds_batch": 23.45515908394009, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.592653512954712, "target_z": 2.4375000085870275, "ce": 6.070269584655762, "genuineness": 3.6287014484405518, "identity": 0.4218694567680359, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/e13697cb88cf8581b78c21eea80ae0dfe44c74ae9774b9dc91773afeeb9c9ae7.mp3" }, { "id": "emo_Amusement-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-0", "key": "e1e5a31ffd1b3376f43fef4be5b1775ebb8c4408481e2dfebb882a8ce1e387c7", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The door is still open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "e7ce2ba733e9c66b58756fd9b18825c32b67a69e1d36da2a5f7a5896eec1fd4b", "generation_seconds_batch": 23.295016126008704, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4606343507766724, "target_z": 1.132812494633108, "ce": 6.1894097328186035, "genuineness": 4.011539936065674, "identity": 0.4774320721626282, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/e1e5a31ffd1b3376f43fef4be5b1775ebb8c4408481e2dfebb882a8ce1e387c7.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": "e224515d18e265850d7a2cb97499d5eab9c106e53310f8980017954f62cd380c", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Someone moved the little blue chair.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e2acde593ac64453e839cbd1af1f273aa18c3c06f815441c9594da79663f1570", "generation_seconds_batch": 20.19552803901024, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.419963002204895, "target_z": 1.0859374924863512, "ce": 6.467403411865234, "genuineness": 4.444586753845215, "identity": 0.37488341331481934, "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_Amusement/e224515d18e265850d7a2cb97499d5eab9c106e53310f8980017954f62cd380c.mp3" }, { "id": "emo_Amusement-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-1", "key": "e2b8aaed7d8736376f591a09acc1e873cff426b31058883a39319a8fac8e7c59", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "13d6f6688e917e04589ce03ab27a93ce01271770e3cfd3bec02f071ee1be4d75", "generation_seconds_batch": 22.623030257993378, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8266764879226685, "target_z": 1.5546875139539194, "ce": 6.062326908111572, "genuineness": 4.030367851257324, "identity": 0.4976455569267273, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/e2b8aaed7d8736376f591a09acc1e873cff426b31058883a39319a8fac8e7c59.mp3" }, { "id": "emo_Amusement-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-0", "key": "e2c39341941b60cd6d07828b3dd536f2b1e70f80b39c0315ab4301ada66a24c4", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The door is still open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7043d3522a82bfc54a8aa43fd240cd8c3ea8f771e0ceb0bf29f894f84efb0359", "generation_seconds_batch": 28.21448022790719, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.945138454437256, "target_z": 2.843749935597295, "ce": 5.967014789581299, "genuineness": 3.5596652030944824, "identity": 0.21279561519622803, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/e2c39341941b60cd6d07828b3dd536f2b1e70f80b39c0315ab4301ada66a24c4.mp3" }, { "id": "emo_Amusement-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-0", "key": "e2cbbb4f8007c6aa3a8320d75662b314ffb62e16366afb72f4e54d1d88fbbc9d", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "32d2d6100517f8d4976c262dc08fa3f85c1b528e9a890ab99aac072f2ffce5b0", "generation_seconds_batch": 17.76061723800376, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.497753620147705, "target_z": 2.32812491198297, "ce": 5.879645347595215, "genuineness": 3.8546390533447266, "identity": 0.46242833137512207, "hypothesis": "La puerta sigue abierta y he dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.06666666666666667, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/e2cbbb4f8007c6aa3a8320d75662b314ffb62e16366afb72f4e54d1d88fbbc9d.mp3" }, { "id": "emo_Amusement-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-1", "key": "e2ddd94900fb3fcdaabe305eb3e39bcd610ce54b09c284736a1b779ea374c3f9", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "13808c97f97ff3e535949802e1a1802ed71165ff19101725d2236f4ff3f1e54b", "generation_seconds_batch": 24.472374593024142, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4299681186676025, "target_z": 2.25, "ce": 5.895530700683594, "genuineness": 4.300237655639648, "identity": 0.4936659336090088, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble what it contient.", "wer": 0.10526315789473684, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/e2ddd94900fb3fcdaabe305eb3e39bcd610ce54b09c284736a1b779ea374c3f9.mp3" }, { "id": "emo_Amusement-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-1", "key": "e456c14dcb4123fb0499abd038015fbb64f6ca1156e2f0684419a2d3224431da", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I found the little box.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It was beside the old window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "46c8e2dd514db3fa2f4026adf4ec11f0b17c7983ff7ffc16fc1168ba66715e0f", "generation_seconds_batch": 17.40225464501418, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7927837371826172, "target_z": 1.5156250579624344, "ce": 6.395919322967529, "genuineness": 4.369274139404297, "identity": 0.2947632074356079, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/e456c14dcb4123fb0499abd038015fbb64f6ca1156e2f0684419a2d3224431da.mp3" }, { "id": "emo_Amusement-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-0", "key": "e47fe29c0c3616230dfbfb6308115c8af97fb89fa1e3067e9eef96e4eb87a0a7", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De deur staat nog open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "fcd8176ac374e3b8257b9d19eb8b493e0ff8d5098844e91d3217a35b9dab852d", "generation_seconds_batch": 22.449645560933277, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0129239559173584, "target_z": 2.921874847580265, "ce": 5.95112943649292, "genuineness": 3.873466968536377, "identity": 0.5744556188583374, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/e47fe29c0c3616230dfbfb6308115c8af97fb89fa1e3067e9eef96e4eb87a0a7.mp3" }, { "id": "emo_Amusement-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-1", "key": "e48d53a732da102ad8e97d1bc4d4ccae834b21ca0bdd92fb74cb68bafa643fb8", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "b2dc6f832878653a54211525fdd7813bb6e970d5d5d896757e9e7863ab5bb7be", "generation_seconds_batch": 24.086964361951686, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7553389072418213, "target_z": 2.6250000171740546, "ce": 5.645336627960205, "genuineness": 4.042920112609863, "identity": 0.4071870446205139, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/e48d53a732da102ad8e97d1bc4d4ccae834b21ca0bdd92fb74cb68bafa643fb8.mp3" }, { "id": "emo_Amusement-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-0", "key": "e49e26680e33465599f5ba71ce27b80fb156d86688e3cd3b247e69bd27690762", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De deur staat nog open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "e7ead54c44080741b79f87257b342079ee1621292806654a968e474ce66af0dc", "generation_seconds_batch": 24.81203827599529, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6097626686096191, "target_z": 1.3046875483020286, "ce": 6.09409761428833, "genuineness": 4.256305694580078, "identity": 0.5249353051185608, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/e49e26680e33465599f5ba71ce27b80fb156d86688e3cd3b247e69bd27690762.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": "e4a09f5bc6f444de3278ccea09018f599623fd59f797eb7fd37d16d5ce5660d7", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fbd8778d86e500cf32fbbb880b1ea67289b763adf986d11e5d57c553a144124c", "generation_seconds_batch": 15.15159706294071, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.863795757293701, "target_z": 2.7499999313037815, "ce": 6.109982967376709, "genuineness": 4.413206577301025, "identity": 0.4892492890357971, "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_Amusement/e4a09f5bc6f444de3278ccea09018f599623fd59f797eb7fd37d16d5ce5660d7.mp3" }, { "id": "emo_Amusement-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-1", "key": "e4c4fa39c0d861cec5d8d3126c3fbf5a69f5e65b7e3a0ad47cd8ec65aac1cfb4", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d27b992ff455f45b6f98e85dac38b7b04d20b5ddd6eee59c8bfc43bd7ccab6eb", "generation_seconds_batch": 21.153170068049803, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.240168571472168, "target_z": 2.0312500815767596, "ce": 6.41180419921875, "genuineness": 4.143336772918701, "identity": 0.5322267413139343, "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_Amusement/e4c4fa39c0d861cec5d8d3126c3fbf5a69f5e65b7e3a0ad47cd8ec65aac1cfb4.mp3" }, { "id": "emo_Amusement-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-0", "key": "e5002ea8dc1408a5fbecf94c756d2b7df78b596f711c7f44dfa69ad8e4313aad", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "d9d33aab0c66ed69440968fddcb6cf31f1ce8a41ae2883892fa0f2b879d2f24c", "generation_seconds_batch": 17.402882663998753, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6739962100982666, "target_z": 2.531250012880541, "ce": 5.673136234283447, "genuineness": 3.7667744159698486, "identity": 0.3754930794239044, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás lista.", "wer": 0.06666666666666667, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/e5002ea8dc1408a5fbecf94c756d2b7df78b596f711c7f44dfa69ad8e4313aad.mp3" }, { "id": "emo_Amusement-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-0", "key": "e5482569ade5df1628937baaf73ef97adc11d3be0f786cb2dd5c8b5016732c12", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "5331f676254aed6abbaa44110e5ddbe8735c010c11ae09789751f58d3832f979", "generation_seconds_batch": 16.713281935080886, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8944621086120605, "target_z": 1.6328125633293264, "ce": 5.824047088623047, "genuineness": 3.8295347690582275, "identity": 0.6302753686904907, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/e5482569ade5df1628937baaf73ef97adc11d3be0f786cb2dd5c8b5016732c12.mp3" }, { "id": "emo_Amusement-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-0", "key": "e695393b6eb881a5bb59089550835d8eb1033d5e9c91bdbb12978e735bfe1133", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "742b9f19f1dd152be09b316a767d6101f89f99bde98c60175ba5d832361a17d6", "generation_seconds_batch": 23.445438673952594, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2877811193466187, "target_z": 0.9335937355093914, "ce": 6.268836498260498, "genuineness": 4.256305694580078, "identity": 0.6130490303039551, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/e695393b6eb881a5bb59089550835d8eb1033d5e9c91bdbb12978e735bfe1133.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_Amusement", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": "f51b71bea1ef713a1a9c77f5785f5ed4de8bf05b8c2b6831516c04661b09702f", "generation_seconds_batch": 17.503765247995034, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6556805968284607, "target_z": 0.20507810004395183, "ce": 6.41180419921875, "genuineness": 4.344170093536377, "identity": 0.376007616519928, "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_Amusement/e6f1e80cc6606ef00fdc322d5829b94fd65ad80a74ab015f88321e5dc194804c.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": "e705dae6293fe16285059fd8d7725da5cce3a06612f52cacc8c48fd0bd612b90", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d4297e034ea5a9b33e8cf28d74cafc95c9458aaf52790bde7bd993a4e7d1711e", "generation_seconds_batch": 15.089088803972118, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.665848433971405, "target_z": 0.21679685058064105, "ce": 6.046441555023193, "genuineness": 4.030367851257324, "identity": 0.7741970419883728, "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_Amusement/e705dae6293fe16285059fd8d7725da5cce3a06612f52cacc8c48fd0bd612b90.mp3" }, { "id": "emo_Amusement-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-1", "key": "e81662cfe2dbc67ac0c2c2fce75b10fbd13a33853c5c98e4ea49d3d7ffb4d1ae", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "73241491ed5e948a788b3d242ae708fddd2c557dcad45c6432b9bc02e7871603", "generation_seconds_batch": 16.536964047001675, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7114410400390625, "target_z": 1.4218750536689209, "ce": 6.467403411865234, "genuineness": 3.9048471450805664, "identity": 0.4667246639728546, "hypothesis": "Encontra la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.11764705882352941, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/e81662cfe2dbc67ac0c2c2fce75b10fbd13a33853c5c98e4ea49d3d7ffb4d1ae.mp3" }, { "id": "emo_Amusement-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-1", "key": "e829ed9ff5f842b18926d1616ed6a48457b69a8cab02b9b20e84e551b4f1965e", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I found the little box.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It was beside the old window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3e0bbb695cb3ac4d1f0a25b008d18c1e138b8682c9e7c384feaf8ecf222fddf5", "generation_seconds_batch": 23.818493850063533, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.131711483001709, "target_z": 1.9062498926621585, "ce": 6.086154937744141, "genuineness": 3.71028995513916, "identity": 0.24477744102478027, "hypothesis": "I found a little box. It was beside the old window. We can look inside together.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/e829ed9ff5f842b18926d1616ed6a48457b69a8cab02b9b20e84e551b4f1965e.mp3" }, { "id": "emo_Amusement-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-1", "key": "e84b7975882a4f9ecabf2fc934c0241370629e140522296ab12836425036c531", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "c04db01cd438355b420dca6d1e72beb4bf241bbe5b809b699ccdaf3ce43d623c", "generation_seconds_batch": 23.47273508796934, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2572776079177856, "target_z": 0.8984374838993238, "ce": 6.252951145172119, "genuineness": 4.457139015197754, "identity": 0.6786056756973267, "hypothesis": "J'ai trouvé la 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_Amusement/e84b7975882a4f9ecabf2fc934c0241370629e140522296ab12836425036c531.mp3" }, { "id": "emo_Amusement-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-1", "key": "e87bcfc5be63913b2fddb5d23046e91c0e664e406996ac84901e966cf8d09fb1", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "02d284f1017ceb0f734f20a29ac35756c9c781180829b04738496ab14f42f27a", "generation_seconds_batch": 22.134898493997753, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2504990100860596, "target_z": 0.8906249377440519, "ce": 6.324435234069824, "genuineness": 4.093128204345703, "identity": 0.43575674295425415, "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_Amusement/e87bcfc5be63913b2fddb5d23046e91c0e664e406996ac84901e966cf8d09fb1.mp3" }, { "id": "emo_Amusement-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-0", "key": "e893caed5632674923e5df8ef7ed750fb2d0d5399cdf37887e37f84b257d41d5", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De deur staat nog open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "7c47a3fe0ddeaae48cea6905893a98ee6b511ba681341bb205fd1c13d6fa19f3", "generation_seconds_batch": 23.91568974603433, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2130541801452637, "target_z": 1.999999896955672, "ce": 5.927301406860352, "genuineness": 3.898571252822876, "identity": 0.6821271181106567, "hypothesis": "De deur 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_Amusement/e893caed5632674923e5df8ef7ed750fb2d0d5399cdf37887e37f84b257d41d5.mp3" }, { "id": "emo_Amusement-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-0", "key": "e8cfae289d20d4226bf8c1babe87ee7100978f72c55356d1ddfd92d62ea36b49", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "2836aa33453c0790a0cec14f2abd9dd7c4086f62228697f3c54d46907f3db5a1", "generation_seconds_batch": 17.246657934971154, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.958695650100708, "target_z": 2.8593750279078387, "ce": 6.213237762451172, "genuineness": 4.400654315948486, "identity": 0.6617095470428467, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/e8cfae289d20d4226bf8c1babe87ee7100978f72c55356d1ddfd92d62ea36b49.mp3" }, { "id": "emo_Amusement-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-0", "key": "e8d5881654187ea76284641d53100841d71f33f17403e49bde36be4a7e3f03e7", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The door is still open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "dc15409eb2143dc41cddc787b861e390d5b357ce00771a289b2b6a2b90ef565e", "generation_seconds_batch": 23.88221506390255, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.179161548614502, "target_z": 1.9609375783566243, "ce": 6.117925643920898, "genuineness": 3.7542223930358887, "identity": 0.37593650817871094, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/e8d5881654187ea76284641d53100841d71f33f17403e49bde36be4a7e3f03e7.mp3" }, { "id": "emo_Amusement-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-1", "key": "e92dcb5c361fb9fbc7c945432f7e36925a13b7583301f2a5cc48843b25bc148f", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "df5242c9e49e94eea416d3f8e24846552a5f2e9932a92dc6ed83affcb17a8c42", "generation_seconds_batch": 21.666609402978793, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.375739574432373, "target_z": 2.1874999055426994, "ce": 6.173524379730225, "genuineness": 4.231201171875, "identity": 0.639960765838623, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/e92dcb5c361fb9fbc7c945432f7e36925a13b7583301f2a5cc48843b25bc148f.mp3" }, { "id": "emo_Amusement-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-0", "key": "e96dfbc1febe1c2087761cb21e9150a485810ec6dc502d246bdd05bb373ed25a", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De deur staat nog open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "ae710b9932af57e3707758726fec26a20f5c078119000a296637b175448d9346", "generation_seconds_batch": 18.153017973992974, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.497753620147705, "target_z": 2.32812491198297, "ce": 6.09409761428833, "genuineness": 4.2751336097717285, "identity": 0.5659719705581665, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/e96dfbc1febe1c2087761cb21e9150a485810ec6dc502d246bdd05bb373ed25a.mp3" }, { "id": "emo_Amusement-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-1", "key": "e9953e187ca342a377fe185fa03434ff0b6b9a9952aa5f3896f371fad8fedbe7", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "1fedff23ba0a8ae42b4089e34e9c85114082f72f6be515b85893ad3de9bed467", "generation_seconds_batch": 17.297067906009033, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.26744544506073, "target_z": 0.910156234436013, "ce": 6.38003396987915, "genuineness": 4.13078498840332, "identity": 0.7042698264122009, "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_Amusement/e9953e187ca342a377fe185fa03434ff0b6b9a9952aa5f3896f371fad8fedbe7.mp3" }, { "id": "emo_Amusement-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-0", "key": "e9b232aadd866ea375ce1f43f598d76ccd0b1934e12751eaf3822bbcbf293a67", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "d17fed7534d5d127ccc9128439d2deb9249beab5f8a71a5ae0ccbfd82f61cc6c", "generation_seconds_batch": 22.32041623000987, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1081494092941284, "target_z": 0.7265625676228402, "ce": 6.332377910614014, "genuineness": 4.507347106933594, "identity": 0.28440824151039124, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/e9b232aadd866ea375ce1f43f598d76ccd0b1934e12751eaf3822bbcbf293a67.mp3" }, { "id": "emo_Amusement-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-1", "key": "e9c10a054e2817a7acb3dec0189795889899eec250d43c3e4423730857217616", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "2c60219f00e287344b2b5b28b474dcdfe1d684b8f944c98738a1a4219973b7f1", "generation_seconds_batch": 23.195080123026855, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3621826171875, "target_z": 2.17187508801703, "ce": 6.054384231567383, "genuineness": 4.042920112609863, "identity": 0.5640321373939514, "hypothesis": "J'ai trouvé la 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_Amusement/e9c10a054e2817a7acb3dec0189795889899eec250d43c3e4423730857217616.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_Amusement", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": "ae10d903c7ae68c06d74a2a15ac3d3a8a6d779542a880c29516cc9ec4e050e60", "generation_seconds_batch": 17.594678697991185, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8302284479141235, "target_z": 0.40624996135837704, "ce": 6.38003396987915, "genuineness": 4.394378662109375, "identity": 0.5110368728637695, "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_Amusement/e9d266c3907611a53d0c5f7688a7e231bba29ead6f87b8ae8d29cb37ab2fae41.mp3" }, { "id": "emo_Amusement-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-1", "key": "ea7f80f634ccc5f1fb15e5ae879e22724cd9d6d6b836c7fc952650fd4bfddcf8", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I found the little box.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It was beside the old window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "c81caa70b0c88d186bff9066114458470c4410114a7e0f8384e138d29f8527d2", "generation_seconds_batch": 22.595749531988986, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0910401344299316, "target_z": 1.8593748905154017, "ce": 6.3641486167907715, "genuineness": 4.281409740447998, "identity": 0.5763280987739563, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/ea7f80f634ccc5f1fb15e5ae879e22724cd9d6d6b836c7fc952650fd4bfddcf8.mp3" }, { "id": "emo_Amusement-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-1", "key": "eacf56924ca073987688117c316edecd1e5e3c58440a3dfc690897fa9573d341", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I found the little box.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It was beside the old window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "bb7863b26d93cf17fcd9c3cc86a530889de8595697ee72290a1c601fdd5f8934", "generation_seconds_batch": 18.731730713974684, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8095672130584717, "target_z": 2.687499836846481, "ce": 6.316492557525635, "genuineness": 4.344170093536377, "identity": 0.30219554901123047, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/eacf56924ca073987688117c316edecd1e5e3c58440a3dfc690897fa9573d341.mp3" }, { "id": "emo_Amusement-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-0", "key": "eafc8b14ab683e00436715f4c5c98742e297ffe3aad7cd78432b9d06bfeea436", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "480450f404108743ab83142a31f376e74b0e966e2a5ad329ceb9f9a297ec78dc", "generation_seconds_batch": 23.227408646955155, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.175934910774231, "target_z": 0.8046874796058101, "ce": 5.617537498474121, "genuineness": 3.760498285293579, "identity": 0.43683916330337524, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/eafc8b14ab683e00436715f4c5c98742e297ffe3aad7cd78432b9d06bfeea436.mp3" }, { "id": "emo_Amusement-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-0", "key": "eb599bfb1bb261007b036949d44a96e31332db015ad8575ca19ae0fde9e6c73e", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "be5faa81d49c5ab215e1784b7d51d292365ef490ec54600d8f012c7706c23158", "generation_seconds_batch": 24.221248122048564, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0471423864364624, "target_z": 0.656250064402705, "ce": 5.959072113037109, "genuineness": 3.961331605911255, "identity": 0.3689221143722534, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/eb599bfb1bb261007b036949d44a96e31332db015ad8575ca19ae0fde9e6c73e.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": "ebb718221ea38ae996395ea73f9be750a21624720b7b86e4bf9e62eefe03690f", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "30744b13d13b81b222fc1d53b7bab21a44d7e051aa6da5f011c1bd1c926fc0a5", "generation_seconds_batch": 29.769972286070697, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9419119358062744, "target_z": 1.687499974238918, "ce": 6.284721851348877, "genuineness": 4.306513786315918, "identity": 0.5990663766860962, "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_Amusement/ebb718221ea38ae996395ea73f9be750a21624720b7b86e4bf9e62eefe03690f.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_Amusement", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": "e111140c530490ecfe3e093e7f3575ca6a43211c7bbe348bfa124be851d3a25e", "generation_seconds_batch": 17.693145637982525, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19134941697120667, "target_z": -0.3300781172180065, "ce": 6.070269584655762, "genuineness": 4.545003414154053, "identity": 0.7621083855628967, "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_Amusement/ebe89981a89e9506d02bacdfa583f9bfe1f04faa699193749ab6419de85c588f.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": "ec0a768f08e8860ab7d70722a3321118d7a4f19e2de568b0c28cfa17e6ed2a86", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "92c24007cfb2ad8cf84ddc4d5d3d0824f11fe85c478761e249d7035c05d90de4", "generation_seconds_batch": 20.169260118040256, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4570822715759277, "target_z": 2.281249909836213, "ce": 6.197352409362793, "genuineness": 4.369274139404297, "identity": 0.6607052087783813, "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_Amusement/ec0a768f08e8860ab7d70722a3321118d7a4f19e2de568b0c28cfa17e6ed2a86.mp3" }, { "id": "emo_Amusement-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-1", "key": "ec7d7c59caab29b3b2f811746ce3fcc1294d9ee2385129c0b24d25ae0032bef6", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I found the little box.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It was beside the old window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "4ffe2c125af6c2bbe52756b662f2a058d90edb53f1248c047010e616e39c1334", "generation_seconds_batch": 23.576125795021653, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3621826171875, "target_z": 2.17187508801703, "ce": 6.221180438995361, "genuineness": 3.8922953605651855, "identity": 0.5202152729034424, "hypothesis": "I found little box. It was beside the old window. We can look inside together.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/ec7d7c59caab29b3b2f811746ce3fcc1294d9ee2385129c0b24d25ae0032bef6.mp3" }, { "id": "emo_Amusement-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-0", "key": "ecbefcb702d03ae18a87e14ec7e1cdace755a1f4cb032fdcd4494765633dcb22", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "65d4c430a0bcf8205bee8ebd14cfe3e999ba63733e3f7ea06a7e8ae3ba294cae", "generation_seconds_batch": 23.314232376986183, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4402986764907837, "target_z": 1.1093749935597295, "ce": 6.133810997009277, "genuineness": 4.519899368286133, "identity": 0.5414883494377136, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/ecbefcb702d03ae18a87e14ec7e1cdace755a1f4cb032fdcd4494765633dcb22.mp3" }, { "id": "emo_Amusement-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-1", "key": "ecd1f2c79013a951864ec86b0cd757db328401371ece1c83d72b5e71c3b9b3d8", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "d5cc47fffd6eec51b3b91bcd98ec0a2bd75b79e7f156925b08c5bc98e499ee86", "generation_seconds_batch": 17.77649029402528, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5655391216278076, "target_z": 2.40624982396594, "ce": 6.149696350097656, "genuineness": 4.319066047668457, "identity": 0.8059011101722717, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/ecd1f2c79013a951864ec86b0cd757db328401371ece1c83d72b5e71c3b9b3d8.mp3" }, { "id": "emo_Amusement-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-1", "key": "ed080724c48d066cf06dd7b444488daf5c10d37c351e7755e54795b623b3b627", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "0c8b4e1fb777e520860cadfa98c082fe3f9a3571dc772dcebef77df0026403a9", "generation_seconds_batch": 23.47273508796934, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8470121622085571, "target_z": 1.5781250150272979, "ce": 6.141753673553467, "genuineness": 4.532451152801514, "identity": 0.5773914456367493, "hypothesis": "J'ai trouvé la 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_Amusement/ed080724c48d066cf06dd7b444488daf5c10d37c351e7755e54795b623b3b627.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": "ed3985b9f0c651e43e44cbfe7773f83e9ea4f321009b8057c79a3a1286491672", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Escribí el número en el sobre.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3d86163a53f3ee4e2c81952a64f9276ddb26c1310903572d52b073ef2e70ff62", "generation_seconds_batch": 26.913656300050206, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7317767143249512, "target_z": 1.4453125547422991, "ce": 6.181467056274414, "genuineness": 4.331617832183838, "identity": 0.6018895506858826, "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_Amusement/ed3985b9f0c651e43e44cbfe7773f83e9ea4f321009b8057c79a3a1286491672.mp3" }, { "id": "emo_Amusement-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-0", "key": "ed39dc2210e326eb09d1158264af0ad4053fb064010966b8329ebe71f77f886b", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De deur staat nog open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "ce1081d7e206cf329a16a3c6c8a67344789fad00f46371ab61c4c2bf6c83e34a", "generation_seconds_batch": 22.85491582704708, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.6094369888305664, "target_z": 3.6093747874710735, "ce": 6.133810997009277, "genuineness": 4.281409740447998, "identity": 0.6628904938697815, "hypothesis": "De deur 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_Amusement/ed39dc2210e326eb09d1158264af0ad4053fb064010966b8329ebe71f77f886b.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": "ed3b366fccbe47aeb7a9e64e52eacea67b2d7e20c6065c8135255034848083c5", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b160bea86295adc35e9ff62173e2048a231bdfded9b474099146bf873e29d296", "generation_seconds_batch": 19.976431137067266, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0029189586639404, "target_z": 1.7578124774590533, "ce": 6.308549880981445, "genuineness": 4.369274139404297, "identity": 0.5671019554138184, "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_Amusement/ed3b366fccbe47aeb7a9e64e52eacea67b2d7e20c6065c8135255034848083c5.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": "edae2b9f73798f27391a502140ab849c9bd7441b7b3a5901522a717160e7ec46", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I wrote the number on the envelope.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8347adb932d2e965512fdf7758c010776db3a730e69ac411e4b95ed819ea47ba", "generation_seconds_batch": 20.176264434005134, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7317767143249512, "target_z": 1.4453125547422991, "ce": 6.372091293334961, "genuineness": 4.055472373962402, "identity": 0.41086477041244507, "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_Amusement/edae2b9f73798f27391a502140ab849c9bd7441b7b3a5901522a717160e7ec46.mp3" }, { "id": "emo_Amusement-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-0", "key": "edd389011f66c9bef0c13143ab7804c8ab700a10993881e93e032a26e9f848b6", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The door is still open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "70e42ad954d113d5569c945890efc75c97f65c63875aba06681278a350dbc1b4", "generation_seconds_batch": 20.940044949995354, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0910401344299316, "target_z": 1.8593748905154017, "ce": 6.252951145172119, "genuineness": 3.6349775791168213, "identity": 0.23509253561496735, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/edd389011f66c9bef0c13143ab7804c8ab700a10993881e93e032a26e9f848b6.mp3" }, { "id": "emo_Amusement-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-1", "key": "edf8d18a5e1a5b640eade1533bb257d26c8c4deb0a7615f9b577ecd31340a3a8", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0aa2495f08172455723ccc98f948da159c4ea4aa0560162867e44ef1f6bd9707", "generation_seconds_batch": 21.773747760918923, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6468818187713623, "target_z": 2.4999998282594533, "ce": 5.990842819213867, "genuineness": 3.8169827461242676, "identity": 0.2655842900276184, "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_Amusement/edf8d18a5e1a5b640eade1533bb257d26c8c4deb0a7615f9b577ecd31340a3a8.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": "ee1922f1c548633db943f868690702094c1499a40d07dd2ec73dd7bfeb580e4e", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I wrote the number on the envelope.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3b4487c2f72fd97f6891346d7a41129133856468a790b4898d77aed0edf4077b", "generation_seconds_batch": 15.230817312956788, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.328452467918396, "target_z": 0.9804687376561482, "ce": 6.403861999511719, "genuineness": 3.9425034523010254, "identity": 0.32665735483169556, "hypothesis": "I wrote the number on the envelope, rate it carefully, and check the last two digits. Call me when you have a moment.", "wer": 0.043478260869565216, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/ee1922f1c548633db943f868690702094c1499a40d07dd2ec73dd7bfeb580e4e.mp3" }, { "id": "emo_Amusement-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-0", "key": "ee361f12ee3b005b40bcd1f7728f0024fc54b1d76299c155d86e4cdc9bf8409e", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De deur staat nog open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "e2df751c09da7470366728ccb29c2c9c0efedd26686a3553beb6a5a61799c66d", "generation_seconds_batch": 24.230325113981962, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1994972229003906, "target_z": 1.9843750794300028, "ce": 5.903473377227783, "genuineness": 4.105680465698242, "identity": 0.43862009048461914, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/ee361f12ee3b005b40bcd1f7728f0024fc54b1d76299c155d86e4cdc9bf8409e.mp3" }, { "id": "emo_Amusement-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-0", "key": "ee443d24506f0f0ca9cf834c1edd6e51276ea7626293726472ceb4fee60d41fa", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f8895a4ad0842bcb1b9d826330723c8952155e52e1d26dc3e318a24fa741e926", "generation_seconds_batch": 21.487364273983985, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7860051393508911, "target_z": 1.5078125118071626, "ce": 6.260893821716309, "genuineness": 4.381826400756836, "identity": 0.6196889281272888, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt ?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/ee443d24506f0f0ca9cf834c1edd6e51276ea7626293726472ceb4fee60d41fa.mp3" }, { "id": "emo_Amusement-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-0", "key": "eecd67079cefb8141c3eab573f4768544733b70387d3f9205f88f46b07fb198f", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The door is still open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "c3b7e3083155e5beb2c1ab66eeb5112971a53cf2026b5739590ac55935c953d6", "generation_seconds_batch": 23.866428078967147, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8095672130584717, "target_z": 2.687499836846481, "ce": 6.197352409362793, "genuineness": 3.3745219707489014, "identity": 0.07361310720443726, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/eecd67079cefb8141c3eab573f4768544733b70387d3f9205f88f46b07fb198f.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": "ef238b41f2e7b048a0eab2ef01270c1b3bdddf272efc92723e0823c9bd84ed10", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] The keys are on the kitchen table.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7caae8856ac7c320f2ae64fcbb07babf8dc18166cb01a2d37975c645c898bd63", "generation_seconds_batch": 15.301124754012562, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.267282724380493, "target_z": 2.0624999914129725, "ce": 6.356205940246582, "genuineness": 3.810706615447998, "identity": 0.34809234738349915, "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_Amusement/ef238b41f2e7b048a0eab2ef01270c1b3bdddf272efc92723e0823c9bd84ed10.mp3" }, { "id": "emo_Amusement-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-1", "key": "ef4b2d41d91bb300aaf8665d738e87f81b24f74fa12cb87e435b722ad395652c", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "6e3f4a8096badb9bdfdfbc71284b9a1bfb4d157f2549c40774a5d819d7416250", "generation_seconds_batch": 16.67965994705446, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5826483964920044, "target_z": 1.2734375010733785, "ce": 6.149696350097656, "genuineness": 4.105680465698242, "identity": 0.38969698548316956, "hypothesis": "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_Amusement/ef4b2d41d91bb300aaf8665d738e87f81b24f74fa12cb87e435b722ad395652c.mp3" }, { "id": "emo_Amusement-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-1", "key": "ef7eaebbd1df532c9a9ccee5cb5d94821bf661f0c84e8331b22a2fd5b51c1e86", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "154edc476998e19467f9911f6e2dc259d517ed205043130fbacceb721f91a62e", "generation_seconds_batch": 16.769443109980784, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.985809803009033, "target_z": 2.890624937744052, "ce": 6.181467056274414, "genuineness": 4.017816066741943, "identity": 0.49880021810531616, "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_Amusement/ef7eaebbd1df532c9a9ccee5cb5d94821bf661f0c84e8331b22a2fd5b51c1e86.mp3" }, { "id": "emo_Amusement-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-0", "key": "ef9604539fe9c8810d1b31db6bf5ace647eb3d045535ada4ceb2a030867b7026", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "4d8344e504f6649e31e951d900937ceac6902b4915b1136854427783cbb2aab9", "generation_seconds_batch": 22.84430093097035, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7792266607284546, "target_z": 1.500000103044328, "ce": 6.149696350097656, "genuineness": 4.15588903427124, "identity": 0.8226654529571533, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/ef9604539fe9c8810d1b31db6bf5ace647eb3d045535ada4ceb2a030867b7026.mp3" }, { "id": "emo_Amusement-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-0", "key": "efff2f8ce052bf63f6706268a790b3af52dc768c6f4150b654d18bcdf35f74b9", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b7e7d149613dde8808dd95eaad51632bfe0320131baaf9fe2ab2459bde8a8bc6", "generation_seconds_batch": 23.331489142030478, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.131711483001709, "target_z": 1.9062498926621585, "ce": 6.213237762451172, "genuineness": 4.557555198669434, "identity": 0.6570960283279419, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/efff2f8ce052bf63f6706268a790b3af52dc768c6f4150b654d18bcdf35f74b9.mp3" }, { "id": "emo_Amusement-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-0", "key": "f02af12d4d5bd34274c4b97f4829cfd563e3a160154e877d66a976f6a6663d09", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "5768ccb20b700b9a889992790b97c1d564cb88a51ff02d480bbbb124ac2f0304", "generation_seconds_batch": 24.46483776497189, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5519821643829346, "target_z": 2.3906250064402705, "ce": 6.09409761428833, "genuineness": 4.093128204345703, "identity": 0.46106815338134766, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/f02af12d4d5bd34274c4b97f4829cfd563e3a160154e877d66a976f6a6663d09.mp3" }, { "id": "emo_Amusement-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-1", "key": "f039d1373b7643b2fd3dee09243b775cd20322c4223130460b1f8b1db53ec232", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "1b8ee8dbd7f01537a239387a7d8ecf0f66da20c691a7eb1c430e359f5b474355", "generation_seconds_batch": 20.764672093908302, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0400383472442627, "target_z": 2.9531250322013523, "ce": 6.078212261199951, "genuineness": 4.036643981933594, "identity": 0.5285179615020752, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/f039d1373b7643b2fd3dee09243b775cd20322c4223130460b1f8b1db53ec232.mp3" }, { "id": "emo_Amusement-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-0", "key": "f03a7d2215b5ec103af333d6bf5ef624439caa8bb4bd36ac18075f53a5906310", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "e3058d802cd26cb0be4a00f4819ed4372ce338f6036aae31203f3a682e90ded6", "generation_seconds_batch": 25.341856165090576, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3420095443725586, "target_z": 0.9960936925742547, "ce": 6.292664527893066, "genuineness": 4.300237655639648, "identity": 0.45712512731552124, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/f03a7d2215b5ec103af333d6bf5ef624439caa8bb4bd36ac18075f53a5906310.mp3" }, { "id": "emo_Amusement-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-0", "key": "f09ef946a2ed5634c4363c9d49e621436cb65c30d68de65399341772c001e77f", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De deur staat nog open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "112cee8d9c0f688ebfb24211e8a8305a7b3cf1f82f730bf03663a821186e6605", "generation_seconds_batch": 24.15502780303359, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4164109230041504, "target_z": 2.2343749076894563, "ce": 5.847874641418457, "genuineness": 4.105680465698242, "identity": 0.02095479518175125, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/f09ef946a2ed5634c4363c9d49e621436cb65c30d68de65399341772c001e77f.mp3" }, { "id": "emo_Amusement-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-0", "key": "f144f5d198fd136c846cdd8d37c75ac08bf78c516b46d622ccf8fb8ccb590c28", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "bd9d3f058a0baef60935614e9f5b9b9a91e73b10bd8c2f1feb5616ddb4cf82d1", "generation_seconds_batch": 25.04123555996921, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.823124408721924, "target_z": 2.7031249291570245, "ce": 6.054384231567383, "genuineness": 3.653805732727051, "identity": 0.5069208145141602, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/f144f5d198fd136c846cdd8d37c75ac08bf78c516b46d622ccf8fb8ccb590c28.mp3" }, { "id": "emo_Amusement-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-1", "key": "f145679451578fdf480e21c129581715c178f6806ad2af1bd7c143b5b822b649", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "dd2504da3187da0ef361ec0b438a51564eff3bb9a1755e0c090823fe842b9efc", "generation_seconds_batch": 23.003820789977908, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.253725528717041, "target_z": 2.046874899102429, "ce": 6.213237762451172, "genuineness": 4.093128204345703, "identity": 0.3402141332626343, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/f145679451578fdf480e21c129581715c178f6806ad2af1bd7c143b5b822b649.mp3" }, { "id": "emo_Amusement-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-1", "key": "f1694ba708ccfe115b74365d9f840d0ab348564da154911a03fc3fcc1cdf800e", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "b1acdfe25e860a1605742f2907589386f38efeba922ca0da9c14932ca5d5c1b3", "generation_seconds_batch": 17.33544357609935, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6572126150131226, "target_z": 1.3593750966040574, "ce": 6.2767791748046875, "genuineness": 4.507347106933594, "identity": 0.48754674196243286, "hypothesis": "J'ai trouvé la 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_Amusement/f1694ba708ccfe115b74365d9f840d0ab348564da154911a03fc3fcc1cdf800e.mp3" }, { "id": "emo_Amusement-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-1", "key": "f17c4928a2088a39bdc97a1c46d9afc52de54754acb0a82ec3d6f221a0dc442d", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "dfc2407a5e4d0203420c99fa927e372414f0113d424a4488d37c110044c0e263", "generation_seconds_batch": 19.991976664983667, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5519821643829346, "target_z": 2.3906250064402705, "ce": 6.284721851348877, "genuineness": 4.105680465698242, "identity": 0.6121837496757507, "hypothesis": "J'ai trouvé la 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_Amusement/f17c4928a2088a39bdc97a1c46d9afc52de54754acb0a82ec3d6f221a0dc442d.mp3" }, { "id": "emo_Amusement-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-1", "key": "f1b5b2c9da9e9a4148b029f70fd7ee46cf69fef39e451a952597035067309139", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "29e2e57a06b7df054115d83096ea8eedc198a4857a7eed243214aa053ea97d05", "generation_seconds_batch": 23.01811925007496, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9486905336380005, "target_z": 1.69531252039419, "ce": 6.316492557525635, "genuineness": 4.444586753845215, "identity": 0.7333624958992004, "hypothesis": "J'ai trouvé la 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_Amusement/f1b5b2c9da9e9a4148b029f70fd7ee46cf69fef39e451a952597035067309139.mp3" }, { "id": "emo_Amusement-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-1", "key": "f1c4b614aa8cc84315305fcb1ebec7c3ce79ac1f504f50697074787a1ca74620", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "fb51831e4fc4c9f11b79815e0e21a048561fdbe352e524758d3f4647a3faf442", "generation_seconds_batch": 23.190377993974835, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4570822715759277, "target_z": 2.281249909836213, "ce": 6.3641486167907715, "genuineness": 3.8420867919921875, "identity": 0.5443736910820007, "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_Amusement/f1c4b614aa8cc84315305fcb1ebec7c3ce79ac1f504f50697074787a1ca74620.mp3" }, { "id": "emo_Amusement-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-1", "key": "f20eeb72eb4ee3ce267f68ccba62ff15b7090eaf5d6d65b43bef96b384d00ace", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "b3ad8f4f5a4938dbc20cb4db93fdfb41bfb57d3b12bee788df199442f6ff5c9f", "generation_seconds_batch": 25.116695114062168, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0910401344299316, "target_z": 1.8593748905154017, "ce": 6.268836498260498, "genuineness": 4.507347106933594, "identity": 0.5114640593528748, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/f20eeb72eb4ee3ce267f68ccba62ff15b7090eaf5d6d65b43bef96b384d00ace.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_Amusement", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": "d7fa7cec3df17785f51d2774a973fc4a363eef9d7858aefac20c57f365f4bc09", "generation_seconds_batch": 16.6870182499988, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5578151941299438, "target_z": 0.09228516047642751, "ce": 6.070269584655762, "genuineness": 4.406930446624756, "identity": 0.6703336238861084, "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_Amusement/f21bc0adf2df6aeda4aa5bc68657c60b57559ffed3b647118e970ebfd0ba6ad8.mp3" }, { "id": "emo_Amusement-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-0", "key": "f21e357f7c60de9ec98b22979da3045c65e7cd24372d728fc7c161403af252a2", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "a42b2b8f8c9df40602153d86ce2aaa87af879d4ac17c6fdd20ba9f8621e39adc", "generation_seconds_batch": 23.062264002044685, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9758048057556152, "target_z": 1.7265625676228402, "ce": 6.149696350097656, "genuineness": 4.381826400756836, "identity": 0.47344738245010376, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/f21e357f7c60de9ec98b22979da3045c65e7cd24372d728fc7c161403af252a2.mp3" }, { "id": "emo_Amusement-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-0", "key": "f2d2a46593c438e2882545a5615c49f6f3d85f2554b3adfa0f2064e84b86aff0", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "9a788504f815ebaf7f7561ac90ecdeb6c474248e0780b281bdb36c03183600ed", "generation_seconds_batch": 23.802513358998112, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0368118286132812, "target_z": 1.7968750708429755, "ce": 6.23706579208374, "genuineness": 4.149612903594971, "identity": 0.563008189201355, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/f2d2a46593c438e2882545a5615c49f6f3d85f2554b3adfa0f2064e84b86aff0.mp3" }, { "id": "emo_Amusement-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-0", "key": "f2dac9b6137b53d593f54eebdde6c20e14f913fb3ecc24b76a14dadf00cd197f", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "5280fdc3d684e39f4fb922141136d65bd83529a72b72402bda825c752eeb8d80", "generation_seconds_batch": 18.411084512947127, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7824530601501465, "target_z": 2.656249927010268, "ce": 6.086154937744141, "genuineness": 4.1998209953308105, "identity": 0.6729953289031982, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/f2dac9b6137b53d593f54eebdde6c20e14f913fb3ecc24b76a14dadf00cd197f.mp3" }, { "id": "emo_Amusement-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-1", "key": "f30e257c10203eac54934ea7460de2fc67723a50c4389819208dc9e7c83666ac", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8a5d32fdffdf5c130d37acde796be64a410660eeb246f436f86be96e35e81135", "generation_seconds_batch": 24.33164233097341, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3215112686157227, "target_z": 2.125000085870273, "ce": 6.4515180587768555, "genuineness": 4.042920112609863, "identity": 0.62081378698349, "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_Amusement/f30e257c10203eac54934ea7460de2fc67723a50c4389819208dc9e7c83666ac.mp3" }, { "id": "emo_Amusement-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-0", "key": "f32db3139b84b4e301038fe34dea7f19b15566d52fc8e1783001dc4a512fc053", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a742d332960345b67cc4324642603e6cc7733c86121d799743aa6e5f76a88c91", "generation_seconds_batch": 24.417220689938404, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.118154525756836, "target_z": 1.890625075136489, "ce": 5.9431867599487305, "genuineness": 4.218649387359619, "identity": 0.5838843584060669, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/f32db3139b84b4e301038fe34dea7f19b15566d52fc8e1783001dc4a512fc053.mp3" }, { "id": "emo_Amusement-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-1", "key": "f3e5aac9cc10fab5905888bf46af2c07423ae9c7d70659a8dea69f6f3d942f17", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I found the little box.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It was beside the old window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "eccd8f819cded1dfe65360bbd1484c49d420c2156a6537102a7e11ed0d00056f", "generation_seconds_batch": 21.80685907509178, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.009697437286377, "target_z": 1.765624886221888, "ce": 6.395919322967529, "genuineness": 4.256305694580078, "identity": 0.5028693079948425, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/f3e5aac9cc10fab5905888bf46af2c07423ae9c7d70659a8dea69f6f3d942f17.mp3" }, { "id": "emo_Amusement-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-0", "key": "f42f094adac0bdaed7b9e1075f144217a65d6895aef42d0e514e63680db6ac49", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "0481037ec7d05bc7e602c82618552b84a7c372ae0fbddecb7db8f6683e393587", "generation_seconds_batch": 26.64550759003032, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6504340171813965, "target_z": 1.3515625504487856, "ce": 5.863759994506836, "genuineness": 3.7165660858154297, "identity": 0.7784619331359863, "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_Amusement/f42f094adac0bdaed7b9e1075f144217a65d6895aef42d0e514e63680db6ac49.mp3" }, { "id": "emo_Amusement-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-0", "key": "f49810d91ffe4f5f808116c4091bddf02ba8d8b87349b891fe1f635a43468c73", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De deur staat nog open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "9829e8cfc6e6d7167da4efec7183985ca4938a3ae87baabcfe5e04380b486d30", "generation_seconds_batch": 21.78505861898884, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8773529529571533, "target_z": 2.765625023614325, "ce": 5.839932441711426, "genuineness": 3.8671910762786865, "identity": 0.38088470697402954, "hypothesis": "De deur staan nog open! Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/f49810d91ffe4f5f808116c4091bddf02ba8d8b87349b891fe1f635a43468c73.mp3" }, { "id": "emo_Amusement-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-1", "key": "f49c2b0089ca43eb9fcd8864caed5c5ce0189cefc353a77317ac9c1d5380d35e", "bucket": "emo_Amusement", "phase": "wording", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "9c3dfd2baaf36f722a97ff33109100ddaa4579439bf7b06a0ca23d4a5f89e5d4", "generation_seconds_batch": 17.89434230304323, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7927837371826172, "target_z": 1.5156250579624344, "ce": 6.4912309646606445, "genuineness": 4.105680465698242, "identity": 0.6045616865158081, "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_Amusement/f49c2b0089ca43eb9fcd8864caed5c5ce0189cefc353a77317ac9c1d5380d35e.mp3" }, { "id": "emo_Amusement-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-0", "key": "f4b2f83a9f8076512d9d0f1eebaab43a59ee599ddf6024a5d3ed500ec72286ff", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De deur staat nog open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "447df19f92b450b18c479090717ac5ad984f0d23d072d1522e875df73a075e56", "generation_seconds_batch": 23.358618611004204, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5962055921554565, "target_z": 1.2890625933839222, "ce": 6.054384231567383, "genuineness": 4.093128204345703, "identity": 0.3582006096839905, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/f4b2f83a9f8076512d9d0f1eebaab43a59ee599ddf6024a5d3ed500ec72286ff.mp3" }, { "id": "emo_Amusement-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-0", "key": "f4bbbff39ac819a035208cc9539d8bf327c1283717f3bebc19d8e8027722c627", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "6b1880719bd33604a95a5aedc514e861f4f7b566d5648ebdad822687a3530258", "generation_seconds_batch": 23.632585786050186, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1691563129425049, "target_z": 0.7968749334505383, "ce": 5.903473377227783, "genuineness": 3.6851859092712402, "identity": 0.4582182765007019, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/f4bbbff39ac819a035208cc9539d8bf327c1283717f3bebc19d8e8027722c627.mp3" }, { "id": "emo_Amusement-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-1", "key": "f59eb1cea9a91483d5f8260d3ed61ca2fa251830d8a98f070a7a648540192c95", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "af601abeb1a8cc69ff6726066cedef279ba55eca68e95ea236aa6db7fc64ed05", "generation_seconds_batch": 17.265696394024417, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.375739574432373, "target_z": 2.1874999055426994, "ce": 6.181467056274414, "genuineness": 4.256305694580078, "identity": 0.5169562101364136, "hypothesis": "Te he encontrado la cajita. Estaba junto a la ventaneja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.17647058823529413, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/f59eb1cea9a91483d5f8260d3ed61ca2fa251830d8a98f070a7a648540192c95.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": "f5d3ee02e2fb8f415affa3a39257f04bac795c5bcb72fe20220c9d4ab43422c4", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Your message arrived after I had left.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6d8c8ab29c6a1d537c1ab83892ca552e47c7fad9496dbfdd9b9c35b60fd0d012", "generation_seconds_batch": 15.504822029964998, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0503687858581543, "target_z": 1.8124998883686447, "ce": 6.308549880981445, "genuineness": 4.093128204345703, "identity": 0.34147119522094727, "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_Amusement/f5d3ee02e2fb8f415affa3a39257f04bac795c5bcb72fe20220c9d4ab43422c4.mp3" }, { "id": "emo_Amusement-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-1", "key": "f65c3b5d33e34ee616f745b2d4c39ac117112f4a89bceff4d364a2e619de5c7f", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "d80cfc15d0d9a45564e84835474e691a4f06b66cd242c3e7efa7c85c9c25407f", "generation_seconds_batch": 21.31248984800186, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8605692386627197, "target_z": 1.5937499699454043, "ce": 6.181467056274414, "genuineness": 4.256305694580078, "identity": 0.5400980114936829, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/f65c3b5d33e34ee616f745b2d4c39ac117112f4a89bceff4d364a2e619de5c7f.mp3" }, { "id": "emo_Amusement-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-0", "key": "f6c0ffe0c5cd8f86da0b29bc647b5b8bc337055cca44fffa58aaa9593f600139", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "c31192aea0c9360f0fdec020e37252913bce8e06d6b1e71cb00f102849d8fbcc", "generation_seconds_batch": 24.7968501530122, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9080191850662231, "target_z": 1.6484375182474331, "ce": 6.24500846862793, "genuineness": 4.18726921081543, "identity": 0.49266526103019714, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/f6c0ffe0c5cd8f86da0b29bc647b5b8bc337055cca44fffa58aaa9593f600139.mp3" }, { "id": "emo_Amusement-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-1", "key": "f6f5510d9a8632cf4aae26e674ec2ff678e2eeb3d8814ec6150e0fd813a30d1e", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "1fa8129b885552e547cbc641f2a6bedee3c1ad6b4f0456ae8cec8d1069487e51", "generation_seconds_batch": 19.182055918034166, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3996273279190063, "target_z": 1.0624999914129727, "ce": 6.308549880981445, "genuineness": 4.545003414154053, "identity": 0.5704418420791626, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/f6f5510d9a8632cf4aae26e674ec2ff678e2eeb3d8814ec6150e0fd813a30d1e.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_Amusement", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": "f2a24ec64095eb1dbbacfa6a583977b93eff59fa5e1db0844763415ab2374233", "generation_seconds_batch": 16.94844940607436, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.548071026802063, "target_z": 0.08105470266147012, "ce": 6.09409761428833, "genuineness": 4.582659721374512, "identity": 0.7279741764068604, "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_Amusement/f7a65885d0e107603bdce9d92b5fc3b68a68524db7b0b06f79b6538794e8bf5c.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": "f7cdeb33f9252819cf9b771ab01ab6739e0a26e5f3e3b2bac64f5b4e7d74b6a7", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "d02d286ded88f6261bc130e56eb0e46876cfc1dd876156e566aab42847e1ba5c", "generation_seconds_batch": 20.196450357092544, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7927837371826172, "target_z": 1.5156250579624344, "ce": 6.268836498260498, "genuineness": 4.3881025314331055, "identity": 0.6292917728424072, "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_Amusement/f7cdeb33f9252819cf9b771ab01ab6739e0a26e5f3e3b2bac64f5b4e7d74b6a7.mp3" }, { "id": "emo_Amusement-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-0", "key": "f814fa086c969ee33e8570d053ffd9a137f90e2f4aab275f2abe13c53122f3f2", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "9b46909b7e6e7472dba90cc49fb27bd5f66f0188ebaa220ef2f2982e733205fd", "generation_seconds_batch": 20.060467932955362, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.365734577178955, "target_z": 1.0234375354214877, "ce": 6.205295085906982, "genuineness": 4.3127899169921875, "identity": 0.5816105008125305, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/f814fa086c969ee33e8570d053ffd9a137f90e2f4aab275f2abe13c53122f3f2.mp3" }, { "id": "emo_Amusement-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-0", "key": "f86fd716788c7c70e0b6e3b2e693aa1baf2b0a2a54810493fe5c3ca43842e179", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "ef5e8376b82ad99388d90ed0c6cd36a6bc24411551953f6c5ad8ef1df90a30e2", "generation_seconds_batch": 20.81152436695993, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.47063946723938, "target_z": 2.296875002146757, "ce": 5.824047088623047, "genuineness": 3.8044304847717285, "identity": 0.6324804425239563, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/f86fd716788c7c70e0b6e3b2e693aa1baf2b0a2a54810493fe5c3ca43842e179.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_Amusement", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": "ceefe10459cb80133323ab76d97d1a7dbdcce1ca0501e204387c32c353f37e49", "generation_seconds_batch": 18.065792068024166, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22185292840003967, "target_z": -0.29492186560793887, "ce": 6.173524379730225, "genuineness": 4.419482707977295, "identity": 0.5677782297134399, "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_Amusement/f86feddc7af334e5c3d6691e715ece3168f8e7618bd3b63ca7d0171f412fdf9d.mp3" }, { "id": "emo_Amusement-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-0", "key": "f8bf5aa9711da569a92e5562c7285f61b16171dbc19a04ea84f34b31beef1286", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De deur staat nog open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "cc41f25d64c0854277efd5880b145a66addcbb9fdab61a29a9e5f9067a47a019", "generation_seconds_batch": 20.624441556050442, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.389296770095825, "target_z": 2.203124997853243, "ce": 5.95112943649292, "genuineness": 4.20609712600708, "identity": 0.5732499957084656, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/f8bf5aa9711da569a92e5562c7285f61b16171dbc19a04ea84f34b31beef1286.mp3" }, { "id": "emo_Amusement-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-1", "key": "f8d853f3ccd41d33d7428764424c26dc7d03f844e8ee85991a1021b7ea409feb", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "51060342b8780568cff2bd647a79ccc7c684fb57c12fcc3242b2d1f62cbcd134", "generation_seconds_batch": 24.07742852193769, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.696351945400238, "target_z": 0.25195310219070866, "ce": 6.205295085906982, "genuineness": 4.243753433227539, "identity": 0.641781210899353, "hypothesis": "J'ai trouvé la 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_Amusement/f8d853f3ccd41d33d7428764424c26dc7d03f844e8ee85991a1021b7ea409feb.mp3" }, { "id": "emo_Amusement-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-1", "key": "f8defe4fef4feda28e51bb0049e6bddb3b75bc7827272664fe94aa939ceabbbb", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I found the little box.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It was beside the old window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "506ac0a6b5a1ceeda65d936f55b1a37f639a2b7a1233e38519ce97d3fd2eb57d", "generation_seconds_batch": 17.40225464501418, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8198978900909424, "target_z": 1.5468749677986475, "ce": 6.308549880981445, "genuineness": 4.2249250411987305, "identity": 0.4531151056289673, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/f8defe4fef4feda28e51bb0049e6bddb3b75bc7827272664fe94aa939ceabbbb.mp3" }, { "id": "emo_Amusement-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-1", "key": "f9ade2f7dc3370164a2e29c0d9e2bd0ad38b7af8cd4a1f6cd0a1a6e5be989d89", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "26d0f9da1f1a59c12de763505cbd40a01af47c4f4df96fb9c41aa76494cacd70", "generation_seconds_batch": 15.943938676966354, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4028539657592773, "target_z": 2.218750090163787, "ce": 6.348263263702393, "genuineness": 3.9676074981689453, "identity": 0.4688756763935089, "hypothesis": "Ich hab die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/f9ade2f7dc3370164a2e29c0d9e2bd0ad38b7af8cd4a1f6cd0a1a6e5be989d89.mp3" }, { "id": "emo_Amusement-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-0", "key": "fa36bfa34f8edabfd8653bd16a81ad386f72764271339330a901545a0b3435d3", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "8292136397d170b3b6f2542fc1c3c6b949d8759755809f13c7a46fe4ca522740", "generation_seconds_batch": 16.829551446950063, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2943968772888184, "target_z": 2.093749901249186, "ce": 5.9431867599487305, "genuineness": 3.911123275756836, "identity": 0.3451490104198456, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/fa36bfa34f8edabfd8653bd16a81ad386f72764271339330a901545a0b3435d3.mp3" }, { "id": "emo_Amusement-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-1", "key": "fa4e5abd1e682b43f1531f289236c8bd5f6951e2a00935c2bf69ed28508f6630", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fb4a466b79a7e52f81b4a7a7740c42f55f52cd773dc0f49bf627202b6c19c285", "generation_seconds_batch": 24.943510113982484, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.592653512954712, "target_z": 2.4375000085870275, "ce": 5.911416053771973, "genuineness": 3.603597402572632, "identity": 0.25204968452453613, "hypothesis": "Ich hab die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/fa4e5abd1e682b43f1531f289236c8bd5f6951e2a00935c2bf69ed28508f6630.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": "fa5de358a10a7564a4ff06aa7e58ecddc1d17eadd28dfb3e2ab9d9097f2809e6", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "67578976d6d9326f34e7760fbbc7af335d19a19a336590485fe1fbb58f08269f", "generation_seconds_batch": 22.141370580997318, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7553389072418213, "target_z": 2.6250000171740546, "ce": 6.252951145172119, "genuineness": 4.268857479095459, "identity": 0.6172432899475098, "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_Amusement/fa5de358a10a7564a4ff06aa7e58ecddc1d17eadd28dfb3e2ab9d9097f2809e6.mp3" }, { "id": "emo_Amusement-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-1", "key": "fac84e46a3a16ff140f713da3d4554f37e85d806cc8cd95f111756901e8b0725", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "d47766b463801b5bdecd9ebf5efb30ac27bde986927beac49929f0b4a8f5f340", "generation_seconds_batch": 22.070913912029937, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6978839635849, "target_z": 1.4062500987508142, "ce": 6.340320587158203, "genuineness": 4.356721878051758, "identity": 0.5386772155761719, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/fac84e46a3a16ff140f713da3d4554f37e85d806cc8cd95f111756901e8b0725.mp3" }, { "id": "emo_Amusement-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-1", "key": "fae20a8d05f5858d70371c3c3139213a925dfc839ced13a20aeb5225ee06ab6b", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3a589cc9f6c21f959b05f2053a49ce234d64f5b0cd88be5f40fdca29f7be344a", "generation_seconds_batch": 24.943510113982484, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.741781711578369, "target_z": 2.609374924863511, "ce": 6.332377910614014, "genuineness": 3.6098732948303223, "identity": 0.46014291048049927, "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_Amusement/fae20a8d05f5858d70371c3c3139213a925dfc839ced13a20aeb5225ee06ab6b.mp3" }, { "id": "emo_Amusement-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-1", "key": "fbce755ae7c0887426d2c93a12c753b7720708a3b59ce88a970890b2105ed808", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "03400a29ed7c04eae66aace06f8c4578eceecd391350f9c1691242b2cd45465e", "generation_seconds_batch": 17.33544357609935, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7114410400390625, "target_z": 1.4218750536689209, "ce": 6.316492557525635, "genuineness": 4.337893962860107, "identity": 0.5786267518997192, "hypothesis": "J'ai trouvé la 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_Amusement/fbce755ae7c0887426d2c93a12c753b7720708a3b59ce88a970890b2105ed808.mp3" }, { "id": "emo_Amusement-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-1", "key": "fbe9c10e9f68149660fbf8ad5058cc9b17b2120ec10243d3ecf0c704f8d0882f", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I found the little box.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It was beside the old window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "4b9d155642043a3ebebefdf8f4bff93b86107e952cb492150385e609726c6484", "generation_seconds_batch": 25.433923322940245, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9993669986724854, "target_z": 2.9062500300545957, "ce": 5.863759994506836, "genuineness": 4.21237325668335, "identity": 0.45475903153419495, "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_Amusement/fbe9c10e9f68149660fbf8ad5058cc9b17b2120ec10243d3ecf0c704f8d0882f.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": "fbf83566c28352845e1e935114ab8079075c3f27078e1e81dfc8fa6b7df6f7b7", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "18b835514ab94656e0347811e6f3f3fdafebcd333bf6ac9ba35c63def1323159", "generation_seconds_batch": 26.821413272991776, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.240168571472168, "target_z": 2.0312500815767596, "ce": 6.038498878479004, "genuineness": 4.344170093536377, "identity": 0.567215621471405, "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_Amusement/fbf83566c28352845e1e935114ab8079075c3f27078e1e81dfc8fa6b7df6f7b7.mp3" }, { "id": "emo_Amusement-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-0", "key": "fc7dfa7d3c3ebbcadcd81c3bc9e8e874ad892b42b5cbb88ba6806198f57fc3af", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "d5e3c3de0f13df23a03ab7bc43d49d3c012f0146ca9f21aee2331c2e7034c669", "generation_seconds_batch": 25.114338336046785, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6590698957443237, "target_z": 0.20898437312158777, "ce": 6.181467056274414, "genuineness": 4.049196243286133, "identity": 0.6224642992019653, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/fc7dfa7d3c3ebbcadcd81c3bc9e8e874ad892b42b5cbb88ba6806198f57fc3af.mp3" }, { "id": "emo_Amusement-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-0", "key": "fcb46c1175f659bca78729a71d303cdda24307a05498ab7eda622019146553c7", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "51c5991da565183069149bf65b6174461875309002ad8952c80971c555113956", "generation_seconds_batch": 24.1472569280304, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7824530601501465, "target_z": 2.656249927010268, "ce": 5.71682071685791, "genuineness": 3.553389072418213, "identity": 0.3898302912712097, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/fcb46c1175f659bca78729a71d303cdda24307a05498ab7eda622019146553c7.mp3" }, { "id": "emo_Amusement-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-1", "key": "fcf174e8e362c200e94d9e9f76b29777e92d1b8e05e07b7f7f622da9e91dfe6f", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "724170e27f67cb4e6b830b8635587a8151c80f60838e8c2aff1f98db25c2b5f9", "generation_seconds_batch": 24.005126739037223, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7960102558135986, "target_z": 2.6718750193208116, "ce": 6.078212261199951, "genuineness": 4.124508857727051, "identity": 0.5597208738327026, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/fcf174e8e362c200e94d9e9f76b29777e92d1b8e05e07b7f7f622da9e91dfe6f.mp3" }, { "id": "emo_Amusement-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-0", "key": "fd3f5bb04b0828ddcdf3ffa81834858bfd56ff81841e96a92f9c47df737b69bb", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e221780b31711d7a56d9689ff4bafbc3ad9e540a6d0c7541271e6eb225f34c37", "generation_seconds_batch": 23.803831085911952, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.972252607345581, "target_z": 2.8749998454335084, "ce": 6.078212261199951, "genuineness": 4.13078498840332, "identity": 0.5893815159797668, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi, quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/fd3f5bb04b0828ddcdf3ffa81834858bfd56ff81841e96a92f9c47df737b69bb.mp3" }, { "id": "emo_Amusement-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-en-1", "key": "fd552a422b2a98f32d41176ff9e5be415ec7af567b38921d98232fbaf4af7ca4", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] I found the little box.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] It was beside the old window.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "793112c47f4ce6de9115c1d620d615af636699abb4fe883a2176360dad6019ce", "generation_seconds_batch": 24.69677540997509, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.592653512954712, "target_z": 2.4375000085870275, "ce": 6.109982967376709, "genuineness": 3.6349775791168213, "identity": 0.3413810133934021, "hypothesis": "I found the little box. It was beside the old window. We can look inside together", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/fd552a422b2a98f32d41176ff9e5be415ec7af567b38921d98232fbaf4af7ca4.mp3" }, { "id": "emo_Amusement-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-fr-1", "key": "fdb7d3edfd841a17e05091db7f07c3bc3448e0fc50105b05edb92c1a2ee99f19", "bucket": "emo_Amusement", "phase": "wording", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "d865e825afc6065a631d43ed1ec655bd3e68d0886e0ab32dab9ca2fb2b83a2a7", "generation_seconds_batch": 17.327306136023253, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5216413736343384, "target_z": 1.2031249978532432, "ce": 6.165581703186035, "genuineness": 4.519899368286133, "identity": 0.7509592175483704, "hypothesis": "J'ai trouvé la 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_Amusement/fdb7d3edfd841a17e05091db7f07c3bc3448e0fc50105b05edb92c1a2ee99f19.mp3" }, { "id": "emo_Amusement-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-1", "key": "fe8bf531c92b077e7ff998ea3bf857fc74da2f423548261f471e52d78ee27cc8", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "7acd3e6e293b32795e61a94ca1b6ccbab873ef8b4496d04b4ed1163afba41d89", "generation_seconds_batch": 21.31248984800186, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6468818187713623, "target_z": 2.4999998282594533, "ce": 6.038498878479004, "genuineness": 3.9425034523010254, "identity": 0.5726026296615601, "hypothesis": "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_Amusement/fe8bf531c92b077e7ff998ea3bf857fc74da2f423548261f471e52d78ee27cc8.mp3" }, { "id": "emo_Amusement-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-de-1", "key": "feb79e8cdf3ac782f2b67726a91aa8f3a57a1ba52725504b509f310fe2bbbd72", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "307f6c2a4f5dfb89546bbd5adb958a01a68233d6559ae16e1363235d60909dda", "generation_seconds_batch": 21.356230317032896, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.996140480041504, "target_z": 1.7500000686962185, "ce": 6.419747352600098, "genuineness": 4.118232727050781, "identity": 0.42928093671798706, "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_Amusement/feb79e8cdf3ac782f2b67726a91aa8f3a57a1ba52725504b509f310fe2bbbd72.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": "ff6504217ad53efec752bc0155ea04accf678dea2e050d69a320189517f85d53", "bucket": "emo_Amusement", "phase": "heldout", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c67d69ba338fe743486c8e5cd2051dc0073f480eea474939178591fbade4e361", "generation_seconds_batch": 15.09112862101756, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8334550857543945, "target_z": 1.5625000601091912, "ce": 6.356205940246582, "genuineness": 4.381826400756836, "identity": 0.5691086649894714, "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_Amusement/ff6504217ad53efec752bc0155ea04accf678dea2e050d69a320189517f85d53.mp3" }, { "id": "emo_Amusement-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-nl-0", "key": "ffb89ccc7eb1ffede0ebb1cd375c091f11e0fdb009ce02ce1c96f6a4e05dddd4", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] De deur staat nog open.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "4fc67c1608b8da185619814284c8bfe0cd7f46047942acaa8e85b6101d09f255", "generation_seconds_batch": 24.603451007045805, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3725130558013916, "target_z": 1.0312499441843224, "ce": 6.1020402908325195, "genuineness": 4.281409740447998, "identity": 0.7219609022140503, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/ffb89ccc7eb1ffede0ebb1cd375c091f11e0fdb009ce02ce1c96f6a4e05dddd4.mp3" }, { "id": "emo_Amusement-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Amusement-es-0", "key": "ffef6a4318384c8f16e5b748b44a98a611db1ab03fd60becefdb2b15a5da27d8", "bucket": "emo_Amusement", "phase": "grid", "candidate": "manual-eef73ce58f32", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on the physical release of amusement, allowing the voice to feel momentarily buoyant.\nSCRIPT:\n(Start with a slight vocal expansion, as if taking a delighted, slightly uneven breath.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the pace to subtly quicken, mirroring the internal rush of genuine laughter.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final sound trail off with a lingering, cheerful vocal brightness.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "98cde59d333c3fd6b0755b63d7bb5403ae352e7e507e407f5e6b9e4c2e9f060b", "generation_seconds_batch": 21.97039549902547, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3081167936325073, "target_z": 0.9570312365827698, "ce": 5.879645347595215, "genuineness": 3.9550557136535645, "identity": 0.46531355381011963, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Amusement/ffef6a4318384c8f16e5b748b44a98a611db1ab03fd60becefdb2b15a5da27d8.mp3" }, { "key": "original-emo_Amusement-de-0-seed1701-scale0.0", "bucket": "emo_Amusement", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "f380d69283cf5c487847e8c9190aa21ecfcb541101d21eec088ea76929954062", "task_id": "emo_Amusement-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 0.4300817549228668, "target_z": -0.054931625966676015, "ce": 6.141753673553467, "genuineness": 4.243753433227539, "identity": 0.6228808164596558, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Amusement/de/640220ea73d612c3c42b52f5.mp3" }, { "key": "original-emo_Amusement-de-0-seed1701-scale0.5", "bucket": "emo_Amusement", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "cb859450a53c2f6e415ee35163fa78aea79e02a58a928573b498f52ce4cd5cbd", "task_id": "emo_Amusement-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 0.5620517730712891, "target_z": 0.09716795030130848, "ce": 6.356205940246582, "genuineness": 4.413206577301025, "identity": 0.27173686027526855, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Amusement/de/965bc23fa2ca5e8dc1266488.mp3" }, { "key": "original-emo_Amusement-de-0-seed1701-scale0.75", "bucket": "emo_Amusement", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "2bb432030e83152af0857659d3feac78785c82521a4ea1f594897022441e5fbf", "task_id": "emo_Amusement-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 0.5590862035751343, "target_z": 0.09375003864162296, "ce": 6.356205940246582, "genuineness": 4.507347106933594, "identity": 0.6248274445533752, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Amusement/de/704ad1addbf4d05e0f7daac3.mp3" }, { "key": "original-emo_Amusement-de-0-seed1701-scale1.0", "bucket": "emo_Amusement", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "47977dcaf479c6b9742f044150caf3eb987bb66f8c42dbe8ce294e5ef23694a7", "task_id": "emo_Amusement-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 0.3722521662712097, "target_z": -0.12158203681815052, "ce": 6.109982967376709, "genuineness": 4.218649387359619, "identity": 0.5328853130340576, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Amusement/de/f57541132a29f6794df7244c.mp3" }, { "key": "original-emo_Amusement-de-0-seed1702-scale0.0", "bucket": "emo_Amusement", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "f06297fa36281d2a697499110ba19cf896b13c5e8a9e9f98acc218b8a7617081", "task_id": "emo_Amusement-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 0.8115874528884888, "target_z": 0.3847656311719259, "ce": 6.316492557525635, "genuineness": 4.532451152801514, "identity": 0.5607538223266602, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Amusement/de/73cd7b72c85e50e338359139.mp3" }, { "key": "original-emo_Amusement-de-0-seed1702-scale0.5", "bucket": "emo_Amusement", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "97777dc2e2a8f1c22d75d85a54265be883b2678441bc32d5ce435c422a5f573f", "task_id": "emo_Amusement-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 0.41716012358665466, "target_z": -0.06982421049840343, "ce": 6.197352409362793, "genuineness": 4.394378662109375, "identity": 0.5392285585403442, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Amusement/de/9bf3bf844e9e138cb49cdacd.mp3" }, { "key": "original-emo_Amusement-de-0-seed1702-scale0.75", "bucket": "emo_Amusement", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "fbe039a92916bb7deea5ee601f0c5d65de4f1effabf2461acd6e18bff92ec56e", "task_id": "emo_Amusement-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 0.2803179621696472, "target_z": -0.22753908437008522, "ce": 6.316492557525635, "genuineness": 4.6203155517578125, "identity": 0.5258910059928894, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Amusement/de/a3923bb145c891a69c6e3cbe.mp3" }, { "key": "original-emo_Amusement-de-0-seed1702-scale1.0", "bucket": "emo_Amusement", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "4dcadb453f3fcf468c64a82efd0990e96aad740baa9b2a23c3474be071b25f03", "task_id": "emo_Amusement-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 0.2540510892868042, "target_z": -0.2578124774590533, "ce": 6.133810997009277, "genuineness": 4.369274139404297, "identity": 0.7050913572311401, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Amusement/de/0675ba54a6b56a7dd95718d0.mp3" }, { "key": "original-emo_Amusement-de-1-seed1701-scale0.0", "bucket": "emo_Amusement", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "d7d191e73c275f1e89fc8b02f6eb91c01ef7c8df51a58cd82681ed17e0d25b89", "task_id": "emo_Amusement-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 0.9488532543182373, "target_z": 0.5429687634172302, "ce": 6.372091293334961, "genuineness": 4.143336772918701, "identity": 0.5074154138565063, "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_Amusement/de/1b9c33df02d62526a4c2c22b.mp3" }, { "key": "original-emo_Amusement-de-1-seed1701-scale0.5", "bucket": "emo_Amusement", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "6dd662db40ff3f51cff67fb6238e80b0643f3f18afd2041d4709e73652f809e8", "task_id": "emo_Amusement-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 0.639581561088562, "target_z": 0.18652345749167298, "ce": 6.3641486167907715, "genuineness": 4.218649387359619, "identity": 0.5793596506118774, "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_Amusement/de/b3fdf0179697d26740b0dda9.mp3" }, { "key": "original-emo_Amusement-de-1-seed1701-scale0.75", "bucket": "emo_Amusement", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "c20b06fe7bd13e6604fadaa8e2e7c3be569ad04f5f8a0bde29034a6425d54ccc", "task_id": "emo_Amusement-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 0.9793567657470703, "target_z": 0.5781250150272979, "ce": 6.403861999511719, "genuineness": 4.243753433227539, "identity": 0.567643404006958, "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_Amusement/de/5096e14ead7f6838c58457f8.mp3" }, { "key": "original-emo_Amusement-de-1-seed1701-scale1.0", "bucket": "emo_Amusement", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "72e9cda864a29188118f2a59aeadbd484b8ce8187fa1b7c1ae7a96022d7c7c57", "task_id": "emo_Amusement-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 0.9590210914611816, "target_z": 0.5546875139539194, "ce": 6.372091293334961, "genuineness": 4.482243061065674, "identity": 0.577643871307373, "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_Amusement/de/cd93119a3c7056ef33de5608.mp3" }, { "key": "original-emo_Amusement-de-1-seed1702-scale0.0", "bucket": "emo_Amusement", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "cef977c331a0b0f97f97ab60c265fb0400d883d6bc2fd5d7c8e237211f0bdb22", "task_id": "emo_Amusement-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 0.8268392086029053, "target_z": 0.4023437569769597, "ce": 6.3641486167907715, "genuineness": 4.337893962860107, "identity": 0.647666871547699, "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_Amusement/de/25fe22270ea39f9fa183a9c3.mp3" }, { "key": "original-emo_Amusement-de-1-seed1702-scale0.5", "bucket": "emo_Amusement", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "106e7138713685d494fab5bd6045f4bf075b59eacae985cb4edaaa3390c85033", "task_id": "emo_Amusement-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 0.9098765254020691, "target_z": 0.49804686346118204, "ce": 6.38797664642334, "genuineness": 4.21237325668335, "identity": 0.5366911292076111, "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_Amusement/de/102d33e0583eb899d7b9a12f.mp3" }, { "key": "original-emo_Amusement-de-1-seed1702-scale0.75", "bucket": "emo_Amusement", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "9e215ccda693c9f6e6bd94566f923f156cb83b08f68be67ef6f7a10eed4386bd", "task_id": "emo_Amusement-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 0.8403962850570679, "target_z": 0.41796871189506624, "ce": 6.23706579208374, "genuineness": 4.6203155517578125, "identity": 0.6781737804412842, "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_Amusement/de/e54f42831d095cbc8a51a9b1.mp3" }, { "key": "original-emo_Amusement-de-1-seed1702-scale1.0", "bucket": "emo_Amusement", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "a96d456c0e379ac117e8671a4325df2fb1ba3be76c7a0eef623a78be38978326", "task_id": "emo_Amusement-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 0.640428900718689, "target_z": 0.1875000429351366, "ce": 6.403861999511719, "genuineness": 4.375550270080566, "identity": 0.5778958201408386, "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_Amusement/de/c2710d9655beaa628a4ddffc.mp3" }, { "key": "original-emo_Amusement-en-0-seed1701-scale0.0", "bucket": "emo_Amusement", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "c128e150414f6aceefc2279120bb9db0d214214ac7c169ae431d27fcceab4804", "task_id": "emo_Amusement-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 0.4561368227005005, "target_z": -0.024902344890464567, "ce": 6.24500846862793, "genuineness": 4.306513786315918, "identity": 0.25828292965888977, "hypothesis": "The 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_Amusement/en/148103996edfe2f30566f630.mp3" }, { "key": "original-emo_Amusement-en-0-seed1701-scale0.5", "bucket": "emo_Amusement", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "8ccf4a968cfbcd04c198573e467365a195e241ed881a290d44a8abf1884ea946", "task_id": "emo_Amusement-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 0.7556643486022949, "target_z": 0.32031250322013527, "ce": 6.197352409362793, "genuineness": 3.7918784618377686, "identity": 0.3391991853713989, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Amusement/en/1540d9ab6e65f1ab10ad42a4.mp3" }, { "key": "original-emo_Amusement-en-0-seed1701-scale0.75", "bucket": "emo_Amusement", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "54d3ea0e6f61d55623813df1b2f8f541b9ad88bdcfe3c2299090c6150011c108", "task_id": "emo_Amusement-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 0.8200606107711792, "target_z": 0.39453121082168785, "ce": 6.292664527893066, "genuineness": 4.017816066741943, "identity": 0.5145866870880127, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Amusement/en/90d15924ae69a09e6742256a.mp3" }, { "key": "original-emo_Amusement-en-0-seed1701-scale1.0", "bucket": "emo_Amusement", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 1.0, "frames_generated": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "9e363fd64d7cf0f3fe43869ece953851d75b1c87970f0efb2aa9038eb6118c5c", "task_id": "emo_Amusement-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 0.8539534211158752, "target_z": 0.4335937355093914, "ce": 6.260893821716309, "genuineness": 4.306513786315918, "identity": 0.3164029121398926, "hypothesis": "The 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_Amusement/en/38fc4ab8fe20c738c1c0aaef.mp3" }, { "key": "original-emo_Amusement-en-0-seed1702-scale0.0", "bucket": "emo_Amusement", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "91c3cd70bf258dabe5a64960e1c418994b63624b79eebaa935a0c4ed42e2da7b", "task_id": "emo_Amusement-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 0.4586787819862366, "target_z": -0.021972657256292265, "ce": 6.117925643920898, "genuineness": 4.011539936065674, "identity": 0.2088569700717926, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Amusement/en/5950dcf0fb5e170fe40fd035.mp3" }, { "key": "original-emo_Amusement-en-0-seed1702-scale0.5", "bucket": "emo_Amusement", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "a6990d5bb57e51cbc08f8813d6d2fc69910b0d632027f04c367c155fb31dcb74", "task_id": "emo_Amusement-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 0.30150097608566284, "target_z": -0.20312499785324317, "ce": 6.173524379730225, "genuineness": 4.262581825256348, "identity": 0.2515350580215454, "hypothesis": "The 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_Amusement/en/79ab0a7a5ef5863a4e02f1f6.mp3" }, { "key": "original-emo_Amusement-en-0-seed1702-scale0.75", "bucket": "emo_Amusement", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "690e1eeb3db3585228de4e4df3aad97cfbedc31f6e720277675626a30969701d", "task_id": "emo_Amusement-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 0.47011759877204895, "target_z": -0.008789062902516905, "ce": 6.221180438995361, "genuineness": 4.080576419830322, "identity": 0.6075693368911743, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Amusement/en/78a09b9310f571b168b0805c.mp3" }, { "key": "original-emo_Amusement-en-0-seed1702-scale1.0", "bucket": "emo_Amusement", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "0ba9c8af21009153a1fd6ebd3f27cc733c1d2c5fa675dc109054a0adffa76f4a", "task_id": "emo_Amusement-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 0.4226676821708679, "target_z": -0.0634765768564363, "ce": 6.213237762451172, "genuineness": 4.105680465698242, "identity": 0.3396172821521759, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Amusement/en/c4ca4f8e5b19e727cf708084.mp3" }, { "key": "original-emo_Amusement-en-1-seed1701-scale0.0", "bucket": "emo_Amusement", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "c8e235c4e75c0585d7f35343e81d40955f9a6586d781d1d07ae86fa25f132f2d", "task_id": "emo_Amusement-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 1.1488206386566162, "target_z": 0.7734374323771598, "ce": 6.38797664642334, "genuineness": 4.18099308013916, "identity": 0.4588179588317871, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Amusement/en/22e1c7b11972cc4b9d119de8.mp3" }, { "key": "original-emo_Amusement-en-1-seed1701-scale0.5", "bucket": "emo_Amusement", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "c34b97dc70a276754ed4437cee723946d76189384cfb7cfd098ce2902e4e5f81", "task_id": "emo_Amusement-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 1.1318743228912354, "target_z": 0.7539062730776359, "ce": 6.38003396987915, "genuineness": 4.394378662109375, "identity": 0.48936355113983154, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Amusement/en/7a3ed91985d5dae31a4b1c85.mp3" }, { "key": "original-emo_Amusement-en-1-seed1701-scale0.75", "bucket": "emo_Amusement", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "ab952f5dd49890fefd99273286a2848f49651824b7fed31ae47ea9ef6fd65e05", "task_id": "emo_Amusement-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 1.3386203050613403, "target_z": 0.9921874881928374, "ce": 6.3641486167907715, "genuineness": 4.281409740447998, "identity": 0.41696107387542725, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Amusement/en/20704472a30f723d20e6cc7d.mp3" }, { "key": "original-emo_Amusement-en-1-seed1701-scale1.0", "bucket": "emo_Amusement", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "517ba63c0db69c7249756e1b825ddd97ba025f2cdf0622d47617d6e1a3fab760", "task_id": "emo_Amusement-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 1.3996273279190063, "target_z": 1.0624999914129727, "ce": 6.395919322967529, "genuineness": 4.325342178344727, "identity": 0.41507747769355774, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Amusement/en/a314c81f3db69d22c85d6172.mp3" }, { "key": "original-emo_Amusement-en-1-seed1702-scale0.0", "bucket": "emo_Amusement", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "3de74446ea671f9fd0168fee13d7159ea568ad3703e4bbadfccaa8c9fee1b9e1", "task_id": "emo_Amusement-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 1.7927837371826172, "target_z": 1.5156250579624344, "ce": 6.24500846862793, "genuineness": 4.344170093536377, "identity": 0.33894672989845276, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Amusement/en/cb28531b86f53c9c1cb04bab.mp3" }, { "key": "original-emo_Amusement-en-1-seed1702-scale0.5", "bucket": "emo_Amusement", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "46759f38e071b8a40fb5ac6f316e9a3f99996866c009821a110c809ee6b4b7a0", "task_id": "emo_Amusement-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 1.2233848571777344, "target_z": 0.8593750279078388, "ce": 6.316492557525635, "genuineness": 4.344170093536377, "identity": 0.5161445140838623, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Amusement/en/3acac80f168dfa4891bf5b3a.mp3" }, { "key": "original-emo_Amusement-en-1-seed1702-scale0.75", "bucket": "emo_Amusement", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "f4429821ec664adda440e3730be8b70309877c83709a60ce60970752f791fb42", "task_id": "emo_Amusement-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 1.0200281143188477, "target_z": 0.6250000171740546, "ce": 6.467403411865234, "genuineness": 4.494794845581055, "identity": 0.42872679233551025, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Amusement/en/8ff3b7d5dbd5045e28b283e3.mp3" }, { "key": "original-emo_Amusement-en-1-seed1702-scale1.0", "bucket": "emo_Amusement", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "260b53a142a36e18af0661c9ae8da32773aa7d689905fc6be6b979d9d5485613", "task_id": "emo_Amusement-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 1.6775482892990112, "target_z": 1.382812597677436, "ce": 6.23706579208374, "genuineness": 4.457139015197754, "identity": 0.5224217176437378, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Amusement/en/6f4d8424d3e13a1c59b93351.mp3" }, { "key": "original-emo_Amusement-es-0-seed1701-scale0.0", "bucket": "emo_Amusement", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "da77f7d1b53292d95044e73a4839f79383f20bfef725629d3b177905c83900e3", "task_id": "emo_Amusement-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 0.6260244250297546, "target_z": 0.17089843387734785, "ce": 6.086154937744141, "genuineness": 4.300237655639648, "identity": 0.5998135209083557, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Amusement/es/c3f2e11f68df1a76cc7a8aba.mp3" }, { "key": "original-emo_Amusement-es-0-seed1701-scale0.5", "bucket": "emo_Amusement", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "cc96e41137e3d36156e47db74e81f0cd0b4b15f30229def4f7740f415aa41218", "task_id": "emo_Amusement-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 0.3328517973423004, "target_z": -0.1669921951478212, "ce": 6.117925643920898, "genuineness": 4.055472373962402, "identity": 0.562016487121582, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Amusement/es/13017a4ab70c099a48db2776.mp3" }, { "key": "original-emo_Amusement-es-0-seed1701-scale0.75", "bucket": "emo_Amusement", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "79a129a7fc59d608efe894d31bb8015272a47b7da03c17b6ed757982d19ee7c1", "task_id": "emo_Amusement-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 0.20490652322769165, "target_z": -0.31445312795179065, "ce": 5.422942161560059, "genuineness": 4.344170093536377, "identity": 0.7708597183227539, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Amusement/es/85b27e2db0708ffc8e000230.mp3" }, { "key": "original-emo_Amusement-es-0-seed1701-scale1.0", "bucket": "emo_Amusement", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "b1ea39c1865ef8151dbe541f4c823ad9b5c63723ddc2b40e79fd8d4fdb8682f6", "task_id": "emo_Amusement-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 0.20999044179916382, "target_z": -0.308593752683446, "ce": 6.054384231567383, "genuineness": 4.030367851257324, "identity": 0.5515260696411133, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Amusement/es/2e89ed7f31751c99f04f1eca.mp3" }, { "key": "original-emo_Amusement-es-0-seed1702-scale0.0", "bucket": "emo_Amusement", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "108b2099233ab5772db2818d238788b600239e047e6e060e1a72854e3a77e5c7", "task_id": "emo_Amusement-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 0.40021371841430664, "target_z": -0.08935547284225522, "ce": 6.0305562019348145, "genuineness": 3.9425034523010254, "identity": 0.4472115635871887, "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_Amusement/es/3e1d428a7d504609a8b72d3f.mp3" }, { "key": "original-emo_Amusement-es-0-seed1702-scale0.5", "bucket": "emo_Amusement", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "b21ed8aa03e73b2fc97bc31d5d2b885573d1f31e3eed5b09e02ddb445696b708", "task_id": "emo_Amusement-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 0.1422048807144165, "target_z": -0.38671873336263457, "ce": 6.0146708488464355, "genuineness": 4.256305694580078, "identity": 0.6502348184585571, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Amusement/es/d7fcc660096459c4a8fa5171.mp3" }, { "key": "original-emo_Amusement-es-0-seed1702-scale0.75", "bucket": "emo_Amusement", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "a8f76beeaac27f40f86d8b584caef31aabd1a9fcf7e1dacac5e6e00cf1e18325", "task_id": "emo_Amusement-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 0.24218858778476715, "target_z": -0.2714843817086151, "ce": 6.109982967376709, "genuineness": 3.7416701316833496, "identity": 0.4301655888557434, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Amusement/es/d78ab3e2f7389780187fa1a9.mp3" }, { "key": "original-emo_Amusement-es-0-seed1702-scale1.0", "bucket": "emo_Amusement", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "04e71819c58b4376b579ef80d9157c9a55c844870d17f951721f073ce4798194", "task_id": "emo_Amusement-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 0.31675273180007935, "target_z": -0.18554687204820935, "ce": 6.09409761428833, "genuineness": 4.381826400756836, "identity": 0.5684574246406555, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Amusement/es/87fe9854e82c4bcddf27e6be.mp3" }, { "key": "original-emo_Amusement-es-1-seed1701-scale0.0", "bucket": "emo_Amusement", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "da6bf819a447843deebe1a46e6876c8aba08904e4fd50e28a735d68d90bbfa83", "task_id": "emo_Amusement-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 0.7997249364852905, "target_z": 0.3710937097483094, "ce": 5.990842819213867, "genuineness": 4.432034492492676, "identity": 0.7436395883560181, "hypothesis": "He encontrado la caquita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.058823529411764705, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Amusement/es/e798660f55ce4fe4053d0b64.mp3" }, { "key": "original-emo_Amusement-es-1-seed1701-scale0.5", "bucket": "emo_Amusement", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "08e76825d48e7419c46bb02264df417b82c3632cd7caf3c82735c5595158da08", "task_id": "emo_Amusement-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 0.3023483157157898, "target_z": -0.20214841240977954, "ce": 6.141753673553467, "genuineness": 4.331617832183838, "identity": 0.6734123229980469, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Amusement/es/a65e7798833801cb588f2a9f.mp3" }, { "key": "original-emo_Amusement-es-1-seed1701-scale0.75", "bucket": "emo_Amusement", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "a6f55d3f411d28b8c51a3de99cbecfe744ba1a111d7e4cade4e5d5184de5b5e0", "task_id": "emo_Amusement-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 0.5980628728866577, "target_z": 0.13867186990145253, "ce": 5.998785495758057, "genuineness": 4.595211505889893, "identity": 0.6961246728897095, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Amusement/es/27449aa34cf7b53e264cb2d1.mp3" }, { "key": "original-emo_Amusement-es-1-seed1701-scale1.0", "bucket": "emo_Amusement", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "06bc313f0e7f59223d7db0194b66ba1e74b0e7d21c47038465712caafd90b072", "task_id": "emo_Amusement-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 0.6150093078613281, "target_z": 0.1582031665934136, "ce": 6.23706579208374, "genuineness": 4.532451152801514, "identity": 0.6883649826049805, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Amusement/es/0299f156c82ac9c6dce6a326.mp3" }, { "key": "original-emo_Amusement-es-1-seed1702-scale0.0", "bucket": "emo_Amusement", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "7c472fc34eed93a991d665092abcd8b8855254d7bdb776763f8601c498565436", "task_id": "emo_Amusement-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 0.41927841305732727, "target_z": -0.06738281558596294, "ce": 6.078212261199951, "genuineness": 4.557555198669434, "identity": 0.6751900911331177, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Amusement/es/c6aecf70c822fcac4746f057.mp3" }, { "key": "original-emo_Amusement-es-1-seed1702-scale0.5", "bucket": "emo_Amusement", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "353eaf55fcf0495e43df7050ca3f7c2a3957510737c2c72a2ad0c3075c25a760", "task_id": "emo_Amusement-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 0.49257156252861023, "target_z": 0.017089833083301996, "ce": 6.149696350097656, "genuineness": 4.632867813110352, "identity": 0.7554459571838379, "hypothesis": "He encontrontado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.058823529411764705, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Amusement/es/6d96b326cd1f3d9ab1097e2b.mp3" }, { "key": "original-emo_Amusement-es-1-seed1702-scale0.75", "bucket": "emo_Amusement", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "a91cb24716ecb7cd95f123e4561900030796cbaa01ba5c053db729202352e155", "task_id": "emo_Amusement-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 0.4387667775154114, "target_z": -0.044921865607938864, "ce": 6.221180438995361, "genuineness": 4.557555198669434, "identity": 0.6255789995193481, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Amusement/es/4c55f5dfdb0a874ada77a863.mp3" }, { "key": "original-emo_Amusement-es-1-seed1702-scale1.0", "bucket": "emo_Amusement", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "6fb25940d0c4961f4c751111b014140a250d119d71997575545c7c509989cd3a", "task_id": "emo_Amusement-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 1.0776458978652954, "target_z": 0.6914063160127726, "ce": 6.268836498260498, "genuineness": 4.796044826507568, "identity": 0.7106467485427856, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Amusement/es/ba832dabf1afc599bbdb0802.mp3" }, { "key": "original-emo_Amusement-fr-0-seed1701-scale0.0", "bucket": "emo_Amusement", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "2dd5f12b13d8fe0419cb9e9b8a85305d9b4a2bc9274337366b91fbc7abe57922", "task_id": "emo_Amusement-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 0.2303261160850525, "target_z": -0.28515625161006763, "ce": 6.173524379730225, "genuineness": 4.519899368286133, "identity": 0.8227983713150024, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Amusement/fr/36f20417b6b292e39076cce6.mp3" }, { "key": "original-emo_Amusement-fr-0-seed1701-scale0.5", "bucket": "emo_Amusement", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "dc99473c88746e1e890c44a48fdf3228963b776cd18cd7dadd6d2d46b298ab51", "task_id": "emo_Amusement-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 0.40911057591438293, "target_z": -0.07910156612265215, "ce": 6.157639026641846, "genuineness": 4.494794845581055, "identity": 0.7676180601119995, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Amusement/fr/666fce8814af6a28f7c9e7f6.mp3" }, { "key": "original-emo_Amusement-fr-0-seed1701-scale0.75", "bucket": "emo_Amusement", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "bd8738254df9b3ebd2cca74de459baaca67a73c74125da4f819fa8e4851b6808", "task_id": "emo_Amusement-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 0.18965476751327515, "target_z": -0.33203125375682446, "ce": 6.117925643920898, "genuineness": 4.036643981933594, "identity": 0.740585446357727, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Amusement/fr/d10c12e2c2d5a6b1153abbf4.mp3" }, { "key": "original-emo_Amusement-fr-0-seed1701-scale1.0", "bucket": "emo_Amusement", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "05bfe1b2a4cf6cdb5d595fff8a7bbe3335dbbe27574a77b9bf0e8f973b3127cd", "task_id": "emo_Amusement-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 0.5561205744743347, "target_z": 0.09033205828571884, "ce": 6.062326908111572, "genuineness": 4.3127899169921875, "identity": 0.66068035364151, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Amusement/fr/bec2ff4352bfc386d793af5c.mp3" }, { "key": "original-emo_Amusement-fr-0-seed1702-scale0.0", "bucket": "emo_Amusement", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "2738203e97d6f408dbfa142581e4f8e71855da7b5fde90a63f2b8cf1fea000c3", "task_id": "emo_Amusement-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 0.36081334948539734, "target_z": -0.1347656311719259, "ce": 5.974957466125488, "genuineness": 4.231201171875, "identity": 0.6101831793785095, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Amusement/fr/abaf67f9f0a2d1bc5efffffd.mp3" }, { "key": "original-emo_Amusement-fr-0-seed1702-scale0.5", "bucket": "emo_Amusement", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "3da3a6e1b4c13676285f7aa66a6537f136d5260e3acc2352aee1407120db4813", "task_id": "emo_Amusement-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 0.32776787877082825, "target_z": -0.1728515704161658, "ce": 6.1020402908325195, "genuineness": 4.218649387359619, "identity": 0.6049849987030029, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Amusement/fr/afa7c3b43d52c51ceb015a7e.mp3" }, { "key": "original-emo_Amusement-fr-0-seed1702-scale0.75", "bucket": "emo_Amusement", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "fbbb97f882377ade8852d2258506610172c28cac251bb574adbe2a0fbdfbf398", "task_id": "emo_Amusement-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 0.3116688132286072, "target_z": -0.19140624731655395, "ce": 6.0146708488464355, "genuineness": 4.325342178344727, "identity": 0.7463631629943848, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Amusement/fr/013b9ef1b0e513771ccb7e4d.mp3" }, { "key": "original-emo_Amusement-fr-0-seed1702-scale1.0", "bucket": "emo_Amusement", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "48974c3259ddfbc37963511c48cbdbef2b6209c7d0b2cc9bd78c5f91a6f52c7f", "task_id": "emo_Amusement-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 0.23371540009975433, "target_z": -0.28124999570648634, "ce": 6.125868320465088, "genuineness": 4.300237655639648, "identity": 0.827807605266571, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Amusement/fr/e383aabe7a73bb123f4798ee.mp3" }, { "key": "original-emo_Amusement-fr-1-seed1701-scale0.0", "bucket": "emo_Amusement", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "83fc39b7ee67fdc3a59836a7f53c34669577154adc39b1339fc37cca2f084268", "task_id": "emo_Amusement-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 0.6022994518280029, "target_z": 0.1435546597263335, "ce": 6.292664527893066, "genuineness": 4.519899368286133, "identity": 0.7144217491149902, "hypothesis": "J'ai trouvé la 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_Amusement/fr/8c560ba41be787a40ad3f252.mp3" }, { "key": "original-emo_Amusement-fr-1-seed1701-scale0.5", "bucket": "emo_Amusement", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "bcb983fd66e720ddd5c5a14b9a9b9c56c8754a7a7d4657d6525c3b289075eabb", "task_id": "emo_Amusement-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 0.5565441846847534, "target_z": 0.09082028231123207, "ce": 6.181467056274414, "genuineness": 4.570107460021973, "identity": 0.7765240669250488, "hypothesis": "J'ai trouvé la 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_Amusement/fr/79bdcd4b4105b4ad328f5d5b.mp3" }, { "key": "original-emo_Amusement-fr-1-seed1701-scale0.75", "bucket": "emo_Amusement", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "90498ad3b79edf71d9abbd5db7ba4f465e44118a06c2f9b8c5d97ff69ffa3bad", "task_id": "emo_Amusement-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 0.4688466191291809, "target_z": -0.010253906719603056, "ce": 6.109982967376709, "genuineness": 4.444586753845215, "identity": 0.747512936592102, "hypothesis": "J'ai trouvé la petite la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.10526315789473684, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Amusement/fr/394d06ceca01f40d78d4f8c1.mp3" }, { "key": "original-emo_Amusement-fr-1-seed1701-scale1.0", "bucket": "emo_Amusement", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "842a9a78b629450568af4998174df3485e7675eba4ab5c5810ca4a4333a23864", "task_id": "emo_Amusement-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 0.3286151885986328, "target_z": -0.17187501932081148, "ce": 6.1894097328186035, "genuineness": 4.582659721374512, "identity": 0.7268332242965698, "hypothesis": "J'ai trouvé la 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_Amusement/fr/9aae309e43b3bc2435e63601.mp3" }, { "key": "original-emo_Amusement-fr-1-seed1702-scale0.0", "bucket": "emo_Amusement", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "0b0933bf435b323578db2df0bcc963255979585069b4db53d52361b6e6d033f8", "task_id": "emo_Amusement-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 0.5862004160881042, "target_z": 0.12500001717405465, "ce": 5.982900142669678, "genuineness": 4.821148872375488, "identity": 0.7289383411407471, "hypothesis": "J'ai trouvé la 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_Amusement/fr/a0e0c6f460b834a8238ed88c.mp3" }, { "key": "original-emo_Amusement-fr-1-seed1702-scale0.5", "bucket": "emo_Amusement", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "5306ee59570933792a4b828abf50ad638201080c97e53e1f8f61c436eb8af2de", "task_id": "emo_Amusement-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 0.4519002139568329, "target_z": -0.029785169063454835, "ce": 6.38003396987915, "genuineness": 4.808597087860107, "identity": 0.5720440149307251, "hypothesis": "J'ai trouvé la 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_Amusement/fr/7a28ac57281b4d519f524701.mp3" }, { "key": "original-emo_Amusement-fr-1-seed1702-scale0.75", "bucket": "emo_Amusement", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "c8fedae2cca3342cd1c7252bb4ba8aec6b1e421ebf0c54eb251875b140e86f6f", "task_id": "emo_Amusement-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 0.4163127839565277, "target_z": -0.07080079594186706, "ce": 6.221180438995361, "genuineness": 4.444586753845215, "identity": 0.7709003686904907, "hypothesis": "J'ai trouvé la 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_Amusement/fr/d4776306d14b3b1f0f64481e.mp3" }, { "key": "original-emo_Amusement-fr-1-seed1702-scale1.0", "bucket": "emo_Amusement", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "b00cf01b50bf010235d029ee54d48504de8328d17746e75f2d0b80204478778e", "task_id": "emo_Amusement-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 0.5042222142219543, "target_z": 0.030517573797943263, "ce": 6.109982967376709, "genuineness": 4.331617832183838, "identity": 0.734295129776001, "hypothesis": "J'ai trouvé la 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_Amusement/fr/cd7135f04009526ba4d30895.mp3" }, { "key": "original-emo_Amusement-nl-0-seed1701-scale0.0", "bucket": "emo_Amusement", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "ca4ed49674f588f3edf276fc40bdfd19c06ddc7239d2f08b0c9f24697ee7a5a4", "task_id": "emo_Amusement-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0878137350082397, "target_z": 0.7031250665494617, "ce": 6.252951145172119, "genuineness": 4.306513786315918, "identity": 0.6580557823181152, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Amusement/nl/964f5c88ee21482179a1c8fe.mp3" }, { "key": "original-emo_Amusement-nl-0-seed1701-scale0.5", "bucket": "emo_Amusement", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "69b5d2a6c0bf1fdfb6c98be3b7a980af64531daa80f9d34f610d3c510129897c", "task_id": "emo_Amusement-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 0.4213967025279999, "target_z": -0.06494142067352246, "ce": 6.133810997009277, "genuineness": 4.300237655639648, "identity": 0.5668858289718628, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Amusement/nl/062f11dbc77d809ae3b2c009.mp3" }, { "key": "original-emo_Amusement-nl-0-seed1701-scale0.75", "bucket": "emo_Amusement", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "700fd464135a5eda47afca84bc658e062429787e2898d71ac8e1edf19e40022e", "task_id": "emo_Amusement-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 0.2972643971443176, "target_z": -0.20800778767812414, "ce": 6.0305562019348145, "genuineness": 4.293961524963379, "identity": 0.6597938537597656, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Amusement/nl/4261cec25675d3396bcc4d04.mp3" }, { "key": "original-emo_Amusement-nl-0-seed1701-scale1.0", "bucket": "emo_Amusement", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "b1ae144800bee0345bd0bf095a70423d38cb1087da22d244d33b50b206ecf265", "task_id": "emo_Amusement-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 0.40656861662864685, "target_z": -0.08203125375682445, "ce": 6.038498878479004, "genuineness": 4.582659721374512, "identity": 0.3802662491798401, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Amusement/nl/a5f76d367dec93c277ea0b82.mp3" }, { "key": "original-emo_Amusement-nl-0-seed1702-scale0.0", "bucket": "emo_Amusement", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "a04ae34c92907933700fcf730ded7c1b77c4dda48e1cb539cfd579df4f46f994", "task_id": "emo_Amusement-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 0.1794869303703308, "target_z": -0.34375000429351366, "ce": 6.173524379730225, "genuineness": 4.413206577301025, "identity": 0.7405907511711121, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Amusement/nl/ba50f9509b25caf5dfd2fcff.mp3" }, { "key": "original-emo_Amusement-nl-0-seed1702-scale0.5", "bucket": "emo_Amusement", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "34f43fe9a0390519bdb7e1836c2cec0bc69ab6aad4d4cfdd8d62ab6e11e32065", "task_id": "emo_Amusement-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 0.7454965114593506, "target_z": 0.308593752683446, "ce": 6.070269584655762, "genuineness": 4.2374773025512695, "identity": 0.8628842830657959, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Amusement/nl/0614a3c02c6fb5596994721e.mp3" }, { "key": "original-emo_Amusement-nl-0-seed1702-scale0.75", "bucket": "emo_Amusement", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "4910a5b4193c97247e83fb5027839ba6491f582a0d50b4f4e1a740f34b130891", "task_id": "emo_Amusement-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 0.26167696714401245, "target_z": -0.24902341455653637, "ce": 6.117925643920898, "genuineness": 4.262581825256348, "identity": 0.6468751430511475, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Amusement/nl/eaf952b193ad424ae270db2f.mp3" }, { "key": "original-emo_Amusement-nl-0-seed1702-scale1.0", "bucket": "emo_Amusement", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "b21e76d9c6f49e6f797853ec8d743b0096fd1e593111dc20a996a0fe7cf40c43", "task_id": "emo_Amusement-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 0.4677874743938446, "target_z": -0.0114746041758233, "ce": 6.054384231567383, "genuineness": 4.218649387359619, "identity": 0.6775711178779602, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Amusement/nl/c945cfd68e3b2726460f84c0.mp3" }, { "key": "original-emo_Amusement-nl-1-seed1701-scale0.0", "bucket": "emo_Amusement", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "a886bed6d42045037d86ddf04f7047572175d26291fad75da67a57f7606d59d0", "task_id": "emo_Amusement-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 0.8031142950057983, "target_z": 0.3750000515221639, "ce": 6.141753673553467, "genuineness": 4.281409740447998, "identity": 0.7352124452590942, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Amusement/nl/afd66b4e8f55c48a9767c634.mp3" }, { "key": "original-emo_Amusement-nl-1-seed1701-scale0.5", "bucket": "emo_Amusement", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "f3dded233c1ca887b417f1d8465cc3ae19619cab431a04b6906e9d7ca75a27e1", "task_id": "emo_Amusement-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 0.9285175800323486, "target_z": 0.5195312623438518, "ce": 6.1020402908325195, "genuineness": 4.149612903594971, "identity": 0.7151727676391602, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Amusement/nl/bb28ffbf61edc5d6ddc20bc8.mp3" }, { "key": "original-emo_Amusement-nl-1-seed1701-scale0.75", "bucket": "emo_Amusement", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "1bd22a0c0359d2822a15f0e27d01481658409c945124bf63b54fabc421d40303", "task_id": "emo_Amusement-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We kunnen er samen in kijken.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3182846307754517, "target_z": 0.968749987119459, "ce": 6.1020402908325195, "genuineness": 4.268857479095459, "identity": 0.7024423480033875, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Amusement/nl/dc8921031aba1baf4c91286e.mp3" }, { "key": "original-emo_Amusement-nl-1-seed1701-scale1.0", "bucket": "emo_Amusement", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "fd14ac4653eca45bdb7e937bf6dbabbe37148ec352c742ad5801bf4be14e1f86", "task_id": "emo_Amusement-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We kunnen er samen in kijken.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3996273279190063, "target_z": 1.0624999914129727, "ce": 6.046441555023193, "genuineness": 4.030367851257324, "identity": 0.7236691117286682, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Amusement/nl/47f6682b3b8f60cbcc5a2db9.mp3" }, { "key": "original-emo_Amusement-nl-1-seed1702-scale0.0", "bucket": "emo_Amusement", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "0154c9b96b1ce60b429c542b92c430c9e5f3c5e1683d0c21bc385e3b407e73e3", "task_id": "emo_Amusement-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 0.7166876196861267, "target_z": 0.2753906032640871, "ce": 6.070269584655762, "genuineness": 4.356721878051758, "identity": 0.4410112500190735, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Amusement/nl/bd04d8d9aed2f139f276e232.mp3" }, { "key": "original-emo_Amusement-nl-1-seed1702-scale0.5", "bucket": "emo_Amusement", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "e1f6b5acff019d6b60c379ca2dca333bf5fe4e990246168e6677d38edc5fed03", "task_id": "emo_Amusement-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 0.8234499096870422, "target_z": 0.39843748389932376, "ce": 6.205295085906982, "genuineness": 4.344170093536377, "identity": 0.727750301361084, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Amusement/nl/5473d00b88edd3986e7d80bf.mp3" }, { "key": "original-emo_Amusement-nl-1-seed1702-scale0.75", "bucket": "emo_Amusement", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "ec9660ef188635b4687f1abbeb42b6495c5c6eca012ff983a90ab283412edfee", "task_id": "emo_Amusement-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We kunnen er samen in kijken.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.291170358657837, "target_z": 0.9374999398908087, "ce": 6.125868320465088, "genuineness": 4.369274139404297, "identity": 0.48784810304641724, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Amusement/nl/cd1732e7387ec3f363b69c1d.mp3" }, { "key": "original-emo_Amusement-nl-1-seed1702-scale1.0", "bucket": "emo_Amusement", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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 Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "64a187bc0e015659b5192e876f2397ecb0a49e692c23c6206bc249ff5983c0c5", "mp3_sha256": "5a2bacbf9f8a4a9bf35adab28ef9433389b18c7fe919ac8b76140f25bff38609", "task_id": "emo_Amusement-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Amusement. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Amusement. 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 Amusement. 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 Amusement. 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": 0.6802529096603394, "target_z": 0.2333984596384298, "ce": 6.23706579208374, "genuineness": 4.444586753845215, "identity": 0.5060120820999146, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Amusement/nl/bb8bef2a459fcdc35661dd93.mp3" } ], "source_standard_audio_unchanged": true }