{ "complete": true, "report": { "bucket": "emo_Impatience_and_Irritability", "label": "Intense Impatience and Irritability", "definition": { "id": "emo_Impatience_and_Irritability", "category": "emotion", "head": "emo_Impatience_and_Irritability", "pole": "high", "label": "Intense Impatience and Irritability", "floor": 3.0 }, "recipe_status": "direct_manual_recipe", "manual_provenance": [ { "id": "rank4/emotion_impatience_and_irritability/full-v2-sealed/sealed-selected", "mission": "emotion_impatience_and_irritability", "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": 6.220862731933594, "genuineness": 4.089708042144776, "wer": 0.013421021081755231, "identity": 0.5980575236678124, "voiceclap": 0.0218905784515664, "fitness": 0.6827850278861557, "steering_v2": 0.7339072041656391, "raw_target": 1.2198075774312018, "target_cdf": 0.7339072041656391, "family_hit_all": null, "nominal_hit_all": null, "n": 100, "valid_fraction": 0.99, "by_arm": { "reference": { "n": 50, "ce": 6.221418704986572, "genuineness": 4.03595374584198, "wer": 0.009872450871338524, "identity": 0.5980575236678124, "fitness": 0.6975718172102775, "steering_v2": 0.7619689164852758 }, "none": { "n": 50, "ce": 6.220306758880615, "genuineness": 4.143462338447571, "wer": 0.01696959129217194, "identity": null, "fitness": 0.6679982385620339, "steering_v2": 0.7058454918460025 } } } } ], "selected_wording": { "id": "manual-89f8b6c2e4b7", "general": "Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.", "inline": [ "Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.", "Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.", "Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant." ], "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": 4.0 }, "n": 20, "target_z": 0.8505859262180828, "target_raw": 1.0854461923241616, "ce": 5.7921767950057985, "genuineness": 3.956310820579529, "identity": 0.4856452025473118, "wer": 0.017562134502923977, "valid_fraction": 0.95, "identity_delta": -0.045121679082512856, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, "manual_adapter": { "config": { "scale": 1.0, "cfg": 5.0 }, "n": 20, "target_z": 2.0829100986918023, "target_raw": 1.9285202577710152, "ce": 5.657349967956543, "genuineness": 3.7669312953948975, "identity": 0.4998628355562687, "wer": 0.005263157894736842, "valid_fraction": 1, "identity_delta": -0.030904046073555947, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, "grid": [ { "config": { "scale": 0.0, "cfg": 4.0 }, "n": 20, "target_z": 0.8505859262180828, "target_raw": 1.0854461923241616, "ce": 5.7921767950057985, "genuineness": 3.956310820579529, "identity": 0.4856452025473118, "wer": 0.017562134502923977, "valid_fraction": 0.95, "identity_delta": -0.045121679082512856, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 3.0 }, "n": 20, "target_z": -0.09560546515101735, "target_raw": 0.43812510520219805, "ce": 5.971383357048035, "genuineness": 4.205155789852142, "identity": 0.5331352725625038, "wer": 0.0061111111111111106, "valid_fraction": 1, "identity_delta": 0.0023683909326791762, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 2.5 }, "n": 20, "target_z": -0.09790040001383535, "target_raw": 0.4365550637245178, "ce": 5.993424272537231, "genuineness": 4.248460483551026, "identity": 0.5566552504897118, "wer": 0.008333333333333333, "valid_fraction": 1, "identity_delta": 0.02588836885988712, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 2.0 }, "n": 20, "target_z": -0.24248047304665776, "target_raw": 0.337643013894558, "ce": 6.102834582328796, "genuineness": 4.343856227397919, "identity": 0.5202124550938606, "wer": 0.002631578947368421, "valid_fraction": 1, "identity_delta": -0.010554426535964011, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.5 }, "n": 20, "target_z": -0.25278320344405875, "target_raw": 0.3305945724248886, "ce": 6.140959429740906, "genuineness": 4.3385216236114506, "identity": 0.5697132647037506, "wer": 0.0027777777777777775, "valid_fraction": 1, "identity_delta": 0.03894638307392597, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.25 }, "n": 20, "target_z": -0.37939452613655184, "target_raw": 0.24397554397583007, "ce": 6.122294139862061, "genuineness": 4.370843172073364, "identity": 0.5545759320259094, "wer": 0.007894736842105263, "valid_fraction": 1, "identity_delta": 0.023809050396084785, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.0 }, "n": 20, "target_z": -0.5146484386060703, "target_raw": 0.15144383162260056, "ce": 6.141952276229858, "genuineness": 4.3928093910217285, "identity": 0.5718657284975052, "wer": 0.02222222222222222, "valid_fraction": 0.95, "identity_delta": 0.04109884686768055, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 5.0 }, "n": 20, "target_z": 1.8311523309280926, "target_raw": 1.7562843725085258, "ce": 5.6869364976882935, "genuineness": 3.8116480708122253, "identity": 0.4395455405116081, "wer": 0.014910130718954247, "valid_fraction": 1, "identity_delta": -0.09122134111821652, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 5.0 }, "n": 20, "target_z": 2.0829100986918023, "target_raw": 1.9285202577710152, "ce": 5.657349967956543, "genuineness": 3.7669312953948975, "identity": 0.4998628355562687, "wer": 0.005263157894736842, "valid_fraction": 1, "identity_delta": -0.030904046073555947, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 4.0 }, "n": 20, "target_z": 1.2299804588889578, "target_raw": 1.345002645254135, "ce": 5.772568416595459, "genuineness": 3.8364384055137633, "identity": 0.4954993911087513, "wer": 0.016245270037839696, "valid_fraction": 0.95, "identity_delta": -0.03526749052107334, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 4.0 }, "n": 20, "target_z": 1.2297851370809505, "target_raw": 1.3448690190911292, "ce": 5.700786495208741, "genuineness": 3.8525992393493653, "identity": 0.48464120402932165, "wer": 0.016228070175438595, "valid_fraction": 1, "identity_delta": -0.04612567760050297, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 3.0 }, "n": 20, "target_z": 0.46386718622376505, "target_raw": 0.8208790048956871, "ce": 5.94308762550354, "genuineness": 4.080262541770935, "identity": 0.5341071516275406, "wer": 0.008881578947368421, "valid_fraction": 1, "identity_delta": 0.00334026999771595, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 3.0 }, "n": 20, "target_z": 0.37099609787649307, "target_raw": 0.7573427960276604, "ce": 5.980716037750244, "genuineness": 4.123567295074463, "identity": 0.5002156063914299, "wer": 0.021929824561403508, "valid_fraction": 0.95, "identity_delta": -0.030551275238394737, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 2.5 }, "n": 20, "target_z": 0.23979493595187185, "target_raw": 0.6675837054848671, "ce": 6.071659588813782, "genuineness": 4.268543767929077, "identity": 0.5885243386030197, "wer": 0.003125, "valid_fraction": 1, "identity_delta": 0.05775745697319508, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 2.5 }, "n": 20, "target_z": 0.21264648318810148, "target_raw": 0.6490105435252189, "ce": 6.010302424430847, "genuineness": 4.200448751449585, "identity": 0.5227888286113739, "wer": 0.005756578947368421, "valid_fraction": 1, "identity_delta": -0.007978053018450736, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 3.0 }, "n": 20, "target_z": 0.19072263340539386, "target_raw": 0.6340117067098617, "ce": 5.964433550834656, "genuineness": 4.1969968438148495, "identity": 0.4967246577143669, "wer": 0.0027777777777777775, "valid_fraction": 1, "identity_delta": -0.03404222391545773, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 2.5 }, "n": 20, "target_z": 0.02763671916690343, "target_raw": 0.5224391937255859, "ce": 6.02936487197876, "genuineness": 4.256619346141815, "identity": 0.5332767024636269, "wer": 0.013943713450292397, "valid_fraction": 1, "identity_delta": 0.0025098208338022233, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 2.0 }, "n": 20, "target_z": -0.11572265518647083, "target_raw": 0.42436226457357407, "ce": 6.130236792564392, "genuineness": 4.250029468536377, "identity": 0.48860830813646317, "wer": 0.0027777777777777775, "valid_fraction": 1, "identity_delta": -0.042158573493361474, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 2.0 }, "n": 20, "target_z": -0.14946289170979973, "target_raw": 0.40127944350242617, "ce": 6.098267555236816, "genuineness": 4.321262562274933, "identity": 0.5552170611917973, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.024450179561972617, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 2.0 }, "n": 20, "target_z": -0.19658202845079126, "target_raw": 0.36904367059469223, "ce": 6.12864830493927, "genuineness": 4.356408321857453, "identity": 0.5395154640078544, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.008748582378029824, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.5 }, "n": 20, "target_z": -0.2621581993601068, "target_raw": 0.3241808250546455, "ce": 6.093104815483093, "genuineness": 4.34260104894638, "identity": 0.52729882132262, "wer": 0.03435672514619883, "valid_fraction": 0.95, "identity_delta": -0.0034680603072047233, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.5 }, "n": 20, "target_z": -0.28334961251028395, "target_raw": 0.3096830725669861, "ce": 6.089133453369141, "genuineness": 4.287371909618377, "identity": 0.5287679113447666, "wer": 0.003333333333333333, "valid_fraction": 1, "identity_delta": -0.0019989702850580215, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.0 }, "n": 20, "target_z": -0.35380858902793055, "target_raw": 0.2614797368645668, "ce": 6.147512125968933, "genuineness": 4.392495632171631, "identity": 0.49885831475257875, "wer": 0.0027777777777777775, "valid_fraction": 1, "identity_delta": -0.0319085668772459, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.5 }, "n": 20, "target_z": -0.3886718665938656, "target_raw": 0.23762860596179963, "ce": 6.154660534858704, "genuineness": 4.443331551551819, "identity": 0.5464682385325432, "wer": 0.0058823529411764705, "valid_fraction": 1, "identity_delta": 0.015701356902718545, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.25 }, "n": 20, "target_z": -0.3951171835011304, "target_raw": 0.23321914970874785, "ce": 6.156844806671143, "genuineness": 4.349818468093872, "identity": 0.5301016144454479, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.0006652671843767166, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.0 }, "n": 20, "target_z": -0.39775390702424923, "target_raw": 0.2314152792096138, "ce": 6.16955304145813, "genuineness": 4.375550246238708, "identity": 0.5730555549263954, "wer": 0.013157894736842105, "valid_fraction": 0.95, "identity_delta": 0.04228867329657078, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.0 }, "n": 20, "target_z": -0.440136722434065, "target_raw": 0.20241978168487548, "ce": 6.123485589027405, "genuineness": 4.340090668201446, "identity": 0.5420546337962151, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.011287752166390419, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.25 }, "n": 20, "target_z": -0.46396484603871474, "target_raw": 0.1861181676387787, "ce": 6.1348038673400875, "genuineness": 4.360801565647125, "identity": 0.5601542182266712, "wer": 0.003333333333333333, "valid_fraction": 1, "identity_delta": 0.02938733659684658, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.25 }, "n": 20, "target_z": -0.48740234345221184, "target_raw": 0.17008379399776458, "ce": 6.140562295913696, "genuineness": 4.295217001438141, "identity": 0.5443134516477585, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.013546570017933846, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 5.0 }, "n": 20, "target_z": 2.3261718502580577, "target_raw": 2.094943735003471, "ce": 5.559357285499573, "genuineness": 3.647529625892639, "identity": 0.4755470044910908, "wer": 0.017085913312693497, "valid_fraction": 1, "identity_delta": -0.055219877138733865, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 5.0 }, "n": 20, "target_z": 1.9993163638704905, "target_raw": 1.8713309958577156, "ce": 5.5939079284667965, "genuineness": 3.78387656211853, "identity": 0.45923521630465985, "wer": 0.028673245614035087, "valid_fraction": 0.9, "identity_delta": -0.07153166532516479, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 4.0 }, "n": 20, "target_z": 1.2958984271710048, "target_raw": 1.3900993257761, "ce": 5.840130710601807, "genuineness": 3.929637610912323, "identity": 0.4675858311355114, "wer": 0.005409356725146199, "valid_fraction": 1, "identity_delta": -0.06318105049431325, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" } ], "development_standard": [ { "scale": 0.0, "n": 20, "target_z": -0.49575196031871116, "target_raw": 0.1643715426325798, "ce": 6.191395401954651, "genuineness": 4.289882326126099, "identity": 0.5307668816298247, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.0, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "scale": 0.5, "n": 20, "target_z": -0.5103027347536164, "target_raw": 0.15441687256097794, "ce": 6.176304316520691, "genuineness": 4.24908801317215, "identity": 0.5751714378595352, "wer": 0.011601307189542484, "valid_fraction": 0.95, "identity_delta": 0.04440455622971058, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "scale": 0.75, "n": 20, "target_z": -0.5274414017151117, "target_raw": 0.1426917389035225, "ce": 6.205295062065124, "genuineness": 4.405675268173217, "identity": 0.5315876379609108, "wer": 0.0, "valid_fraction": 1, "identity_delta": 0.0008207563310861588, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "scale": 1.0, "n": 20, "target_z": -0.5201171922135612, "target_raw": 0.14770247489213945, "ce": 6.1830556154251095, "genuineness": 4.311534631252289, "identity": 0.5791918650269509, "wer": 0.016666666666666666, "valid_fraction": 0.95, "identity_delta": 0.0484249833971262, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" } ] }, "heldout": { "standard": { "n": 50, "target_z": -0.5380078112169584, "target_raw": 0.13546290576457978, "ce": 6.235000677108765, "genuineness": 4.364127864837647, "identity": 0.583655651807785, "wer": 0.014050254093732353, "valid_fraction": 1, "identity_delta": 0.0, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" }, "manual": { "n": 50, "target_z": 1.371542949713679, "target_raw": 1.441850266456604, "ce": 5.900733318328857, "genuineness": 3.881374888420105, "identity": 0.4974919033050537, "wer": 0.05138518727649162, "valid_fraction": 0.96, "identity_delta": -0.08616374850273133, "identity_pairs": 50, "gates_pass": false, "gate_scope": "heldout_50_reference_pairs" }, "adapter": { "n": 50, "target_z": 2.36089841453798, "target_raw": 2.1187013357877733, "ce": 5.642675924301147, "genuineness": 3.65160906791687, "identity": 0.42866593196988106, "wer": 0.03203044667003477, "valid_fraction": 1, "identity_delta": -0.15498971983790397, "identity_pairs": 50, "gates_pass": false, "gate_scope": "heldout_50_reference_pairs" }, "matched_no_adapter": { "n": 50, "target_z": 2.104296861965387, "target_raw": 1.94315165579319, "ce": 5.717535581588745, "genuineness": 3.7224655294418336, "identity": 0.4748577162623405, "wer": 0.03351200134724162, "valid_fraction": 0.98, "identity_delta": -0.1087979355454445, "identity_pairs": 50, "gates_pass": false, "gate_scope": "heldout_50_reference_pairs" } }, "adapter_vs_matched_cfg": { "n": 50, "delta_z": 0.25660155257259354, "ci95_z": [ 0.11937499199545423, 0.41792969643364486 ], "language_deltas": { "en": 0.2148436950708464, "de": 0.3238280713300651, "fr": 0.11992190089906189, "nl": 0.07109373155415047, "es": 0.5533203640088439 }, "languages_improved": 5, "clear_gain": true, "delta_ce": -0.07485965728759765, "delta_genuineness": -0.07085646152496337, "delta_wer": -0.0014815546772068507, "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": 0.9893554648243013, "ci95_z": [ 0.7558202993190452, 1.2149414293770797 ], "language_deltas": { "en": 0.6166015281777872, "de": 1.0856444711393325, "fr": 1.3152344127425226, "nl": 0.7499999869313538, "es": 1.17929692513051 }, "languages_improved": 5, "clear_gain": true, "delta_ce": -0.25805739402770994, "delta_genuineness": -0.22976582050323485, "delta_wer": -0.019354740606456852, "note": "Exploratory language-cluster bootstrap; five voices, one fixed reference voice per language. No familywise claim across72targets." }, "manual_vs_standard": { "n": 50, "delta_z": 1.9095507609306375, "ci95_z": [ 1.511406249060691, 2.2908593471270278 ], "language_deltas": { "en": 1.269921892186631, "de": 2.456152326571877, "fr": 1.5134765360734277, "nl": 2.074414017151117, "es": 2.2337890326701344 }, "languages_improved": 5, "clear_gain": true, "delta_ce": -0.3342673587799072, "delta_genuineness": -0.4827529764175415, "delta_wer": 0.03733493318275927, "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": 1793023176.379529 }, "rows": [ { "id": "emo_Impatience_and_Irritability-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-0", "key": "002a16068efc19e6f16a95e80090d2b2e7587ec955874605c18f3ca8eaaf4128", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De deur staat nog open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "98cdcde25e208ab9c3d9b5bb74860ac768defdec9f3200beb48040967437d003", "generation_seconds_batch": 18.445135482004844, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6131002306938171, "target_z": 0.16015625918889187, "ce": 5.895530700683594, "genuineness": 3.8546390533447266, "identity": 0.5489999651908875, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/002a16068efc19e6f16a95e80090d2b2e7587ec955874605c18f3ca8eaaf4128.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-1", "key": "00d6cc9e228cf0f9b79d2f63b0bac0b0025c5e2a2bbc3105b7ee2e67ffe56daf", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "92690702eb31a777fc752340c2ae6856320c18c1ae73716f182ca0743732544b", "generation_seconds_batch": 14.069754650001414, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6478413343429565, "target_z": 0.21093744622796615, "ce": 6.213237762451172, "genuineness": 4.507347106933594, "identity": 0.7172591686248779, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/00d6cc9e228cf0f9b79d2f63b0bac0b0025c5e2a2bbc3105b7ee2e67ffe56daf.mp3" }, { "id": "emo_Impatience_and_Irritability-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-0", "key": "014d2e89445e4e1e919fbb1d81eff33b627a6b4e2e87debcf86fa7f5b3a8033c", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The door is still open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "727b299d1ebc7ef4f4789faad9b2071a4ed8e4b2eb303cc4492c9ec11e3684f1", "generation_seconds_batch": 19.679495714022778, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4754718244075775, "target_z": -0.04101564116564309, "ce": 6.268836498260498, "genuineness": 4.174716949462891, "identity": 0.17150142788887024, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/014d2e89445e4e1e919fbb1d81eff33b627a6b4e2e87debcf86fa7f5b3a8033c.mp3" }, { "id": "emo_Impatience_and_Irritability-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-0", "key": "0180569a59c60b3f11645d9c0c2661ac8377b990c7e6165ccb6c6cdbf419e605", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The door is still open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "eb3e330d7f67017dd5edbd5ae47e40526d9a8cd8faad58d5334fc80e0e94fcc5", "generation_seconds_batch": 20.243516954011284, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.65585857629776, "target_z": 0.2226562755246996, "ce": 6.149696350097656, "genuineness": 4.268857479095459, "identity": 0.3711710572242737, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/0180569a59c60b3f11645d9c0c2661ac8377b990c7e6165ccb6c6cdbf419e605.mp3" }, { "id": "emo_Impatience_and_Irritability-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-1", "key": "0180feab5b4d21c49ae917117e0c8c986e1e2fa7d16214f2695a6b2fc93feca7", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "f148efb4b13f02f1d6883ca5a1a70d19d0de50ade594f0907a6b4c41472abd46", "generation_seconds_batch": 13.057030930067413, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2523267865180969, "target_z": -0.36718748706748555, "ce": 6.229123115539551, "genuineness": 4.20609712600708, "identity": 0.48509910702705383, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/0180feab5b4d21c49ae917117e0c8c986e1e2fa7d16214f2695a6b2fc93feca7.mp3" }, { "id": "emo_Impatience_and_Irritability-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-0", "key": "01a723ce84efb3193ab236d8b336effe6107f5186dd544bbccacbeb973885eaf", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La puerta sigue abierta.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "2e66c73591ed68e7bde776535838aea52851784314da32134fa73de1ca42e8a3", "generation_seconds_batch": 19.19352449697908, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.534552812576294, "target_z": 2.968749904707788, "ce": 5.6413655281066895, "genuineness": 3.9425034523010254, "identity": 0.7043215036392212, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/01a723ce84efb3193ab236d8b336effe6107f5186dd544bbccacbeb973885eaf.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_Impatience_and_Irritability", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": "62eff9e554e075108fb3c2c8c6d83933d661b8efc2e47432d2b98a62d42b84a6", "generation_seconds_batch": 17.617465610965155, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0973278284072876, "target_z": -0.5937499809415576, "ce": 6.046441555023193, "genuineness": 4.494794845581055, "identity": 0.4834299385547638, "hypothesis": "J'ai écrit le numéro sur l'enveloppe. L'EMI et vérifie les deux derniers chiffres. Appelle-moi quand tu auras un moment.", "wer": 0.13636363636363635, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/01f5d5f22d9b51f4e674eec92be80d0710e62f5704093e3409bc811236eec3e5.mp3" }, { "id": "emo_Impatience_and_Irritability-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-1", "key": "0242365cb2efd5d88f317595c8ea352b4326f8ce045ad8c87955b2aadc85b560", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "a7d2a6db479d09f5226f2385b05fbfeb1a0d377c34f7a07ddb938a57136f05da", "generation_seconds_batch": 19.673759720055386, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0786210298538208, "target_z": -0.621093770760089, "ce": 6.38003396987915, "genuineness": 4.18099308013916, "identity": 0.553406834602356, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/0242365cb2efd5d88f317595c8ea352b4326f8ce045ad8c87955b2aadc85b560.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-1", "key": "02c3111bb4eb0ffb754bdec6095c7cdc5da13be6632a83a791675f7d01ca0d5e", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "5f97dba6f2ea840f10c74b82ee0356f4a8844fce5ee354601f0a63e94fd19fcb", "generation_seconds_batch": 13.035405406029895, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07060384750366211, "target_z": -0.6328125129325145, "ce": 6.133810997009277, "genuineness": 4.6956281661987305, "identity": 0.723875105381012, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/02c3111bb4eb0ffb754bdec6095c7cdc5da13be6632a83a791675f7d01ca0d5e.mp3" }, { "id": "emo_Impatience_and_Irritability-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-1", "key": "038b07474173c2e1e33454662a901eefd8c3da29689e2346becfde0d02dda252", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "84b479cf0597c17dbe4072dd0edc7e4b34955d37848aee269c8b5e8f357c86b4", "generation_seconds_batch": 18.102000265964307, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08129343390464783, "target_z": -0.6171875088485625, "ce": 6.348263263702393, "genuineness": 4.632867813110352, "identity": 0.40585124492645264, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/038b07474173c2e1e33454662a901eefd8c3da29689e2346becfde0d02dda252.mp3" }, { "id": "emo_Impatience_and_Irritability-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-1", "key": "044ff1f30810b932dd2c430dc2d1c84d462f7c17c42d48856216b7366cd7f29a", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ceabfda02119bae275d009127b0c7a18899e5ab458a348c58d424b6e75b7d39d", "generation_seconds_batch": 18.6792921340093, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3765931725502014, "target_z": -0.18554689627058302, "ce": 5.903473377227783, "genuineness": 4.068024158477783, "identity": 0.40598809719085693, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/044ff1f30810b932dd2c430dc2d1c84d462f7c17c42d48856216b7366cd7f29a.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-0", "key": "0457bb114a25ca05e10b32839e8c01ac46b872a8549e9468f68d826cb6cf2353", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La porte est encore ouverte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "1471807e809ed4dfe2a288a803cbc59befaa8e0702c457b963b1c86b9b473641", "generation_seconds_batch": 18.415875100996345, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.079721689224243, "target_z": 3.765625069427183, "ce": 5.903473377227783, "genuineness": 3.7918784618377686, "identity": 0.4732667803764343, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/0457bb114a25ca05e10b32839e8c01ac46b872a8549e9468f68d826cb6cf2353.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-1", "key": "04c4b49f1af2ae1682092d61a7df9534f4151fbbf622639a4810b25079208b9e", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "77332d726ae70e9834554a78ede6831e6fcbd383850fe7e8643e20d8f25e9b1d", "generation_seconds_batch": 19.083424907992594, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.022930026054382324, "target_z": -0.7695312877765554, "ce": 6.149696350097656, "genuineness": 4.482243061065674, "identity": 0.7406147718429565, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/04c4b49f1af2ae1682092d61a7df9534f4151fbbf622639a4810b25079208b9e.mp3" }, { "id": "emo_Impatience_and_Irritability-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-1", "key": "04e116cec5295e446bb106802b27e36411262919b15b31d2515ceeb35c8f3567", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I found the little box.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "5d94417f8c7e031b177b723c09d46cdbd0360c00d0dfb5ddb7e2ed60ad7ad2d7", "generation_seconds_batch": 14.397804271080531, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.033619582653045654, "target_z": -0.7851562482983534, "ce": 6.372091293334961, "genuineness": 4.369274139404297, "identity": 0.49933844804763794, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/04e116cec5295e446bb106802b27e36411262919b15b31d2515ceeb35c8f3567.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": "0509fa7a6af4bb1e8891ed4a4fb360e40db0bd495b09334edac6ade77c79f6d6", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "df9e68c9dfa5475a8e8f9a657646e7348102b1b8b49937c86e055ef5456973f1", "generation_seconds_batch": 19.720723379054107, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6200695037841797, "target_z": 3.0937499373794037, "ce": 5.879645347595215, "genuineness": 3.4592485427856445, "identity": 0.6401631832122803, "hypothesis": "déplacé la petite chaise bleue elle était ici près de la grande bibliothèque Nous la remettrons après le déjeuner", "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_Impatience_and_Irritability/0509fa7a6af4bb1e8891ed4a4fb360e40db0bd495b09334edac6ade77c79f6d6.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": "056008ae8725a6237b66ec1d204a3413e512592674aa40f9a8ed233c6acb2afb", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "3bde431d52bb155b86fd84d22c4d9e5251178544f9e3630f0a5039387828329a", "generation_seconds_batch": 18.631250304053538, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.213865280151367, "target_z": 2.499999869313538, "ce": 6.022613525390625, "genuineness": 3.948779582977295, "identity": 0.5732362270355225, "hypothesis": "Ik scheep het nummer op de envelop. Lees het goed en controleer de laatste twee cijfers. Bel me wanneer je even tijd hebt.", "wer": 0.043478260869565216, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/056008ae8725a6237b66ec1d204a3413e512592674aa40f9a8ed233c6acb2afb.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_Impatience_and_Irritability", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": "bcc79cf03c9b97ff444f24a680ffe331645e42d82ed78426a4a200a50be54b42", "generation_seconds_batch": 13.654272214975208, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1507757306098938, "target_z": -0.515625004083952, "ce": 6.332377910614014, "genuineness": 4.7332844734191895, "identity": 0.706388533115387, "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_Impatience_and_Irritability/059867605942d1f4c46c2c44d936e08b7fbe89dd4feef4c05500a7ed426c27a3.mp3" }, { "id": "emo_Impatience_and_Irritability-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-0", "key": "059a82216fab87c1c477c000d31e8eef4dd92901722e6af735db08fd575169f5", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Tür ist noch offen.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "38107f65968bceceb01239cd982ed2bdbdf918f37608a1fc5df87f3e8bdb7ea0", "generation_seconds_batch": 13.337640649056993, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2924126982688904, "target_z": -0.3085937762053583, "ce": 5.95112943649292, "genuineness": 4.507347106933594, "identity": 0.5506043434143066, "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_Impatience_and_Irritability/059a82216fab87c1c477c000d31e8eef4dd92901722e6af735db08fd575169f5.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": "05dab25e61332ae6a1211f275a5b3523687589c910610b4ec5eaf47f6dcb89a2", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Your message arrived after I had left.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e0ae99f46dacf498ac87850cef6323abd96a279ff09ab1d3069e6d9fd185d366", "generation_seconds_batch": 15.26596322399564, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4647822380065918, "target_z": -0.05664064524959502, "ce": 6.308549880981445, "genuineness": 4.20609712600708, "identity": 0.4269656538963318, "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_Impatience_and_Irritability/05dab25e61332ae6a1211f275a5b3523687589c910610b4ec5eaf47f6dcb89a2.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-1", "key": "063cbc4775c7eaeb080c034601133cc0ebada259a7c2f63ad9fa67fbb873e860", "bucket": "emo_Impatience_and_Irritability", "phase": "wording", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "33de4cba754ded2ecc38503f5e86bce0ce480013f16c7456eda0961d4bd949e8", "generation_seconds_batch": 14.224763804930262, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0011215806007385254, "target_z": -0.7343749741349711, "ce": 6.213237762451172, "genuineness": 4.557555198669434, "identity": 0.6751932501792908, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/063cbc4775c7eaeb080c034601133cc0ebada259a7c2f63ad9fa67fbb873e860.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": "068ce744fda0562242d3debe32393c340a4582c395fb42b2c5803e5833b65b85", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The road turns left behind the bridge.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "73bafe0681404ff6d8584d0b769b668081eb3020206c2c659f0bde7d59a8574f", "generation_seconds_batch": 13.837683302932419, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3693883419036865, "target_z": 1.265625112989337, "ce": 6.070269584655762, "genuineness": 3.8169827461242676, "identity": 0.7344138622283936, "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_Impatience_and_Irritability/068ce744fda0562242d3debe32393c340a4582c395fb42b2c5803e5833b65b85.mp3" }, { "id": "emo_Impatience_and_Irritability-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-0", "key": "07218999bb92e34192c2733225dbe6798b1310ffe29548ea068d8ce83c5b5bb5", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La puerta sigue abierta.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "194f994e04be36eed8043447c7966aadf3c4368086df1f0b9a7c47c5937dc004", "generation_seconds_batch": 21.349059412023053, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0214529037475586, "target_z": 2.218750057175327, "ce": 5.34748649597168, "genuineness": 3.343141555786133, "identity": 0.5846518874168396, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/07218999bb92e34192c2733225dbe6798b1310ffe29548ea068d8ce83c5b5bb5.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": "08521b4577274cae27537fdf6825f81efb9ef6f36c4419bea7be25f47b60e75b", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b7e74e32cb1ddfa2bd34b9f646a0f1521b765c1e2b3ced96a3a2981a1bd3eaef", "generation_seconds_batch": 18.4100108880084, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.6248903274536133, "target_z": 4.562499885649346, "ce": 5.391171455383301, "genuineness": 3.4812145233154297, "identity": 0.2764340341091156, "hypothesis": "Deine Nachricht kam, als ich schon weg war. Ich lasse sie zweimal. Dann legte ich das Handy weg. Sag mir, wann wir reden können.", "wer": 0.041666666666666664, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/08521b4577274cae27537fdf6825f81efb9ef6f36c4419bea7be25f47b60e75b.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-0", "key": "08961ee530bea0c6b92be82870eec7b9e6240f7733a66a866711790366f17630", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De deur staat nog open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "fac724431bad468c9f5580912f83600ac6d30bd63482c12730f9f7fd5da7b395", "generation_seconds_batch": 18.75419270596467, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6366279125213623, "target_z": 1.6562500844016734, "ce": 6.1894097328186035, "genuineness": 3.7793264389038086, "identity": 0.04199644550681114, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. De deur staat nog open. Ik heb je jas op de stoel gelegd.", "wer": 0.631578947368421, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/08961ee530bea0c6b92be82870eec7b9e6240f7733a66a866711790366f17630.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-0", "key": "09625cbac6e611b99c0021a884481d7fa334a9d3f01a83b81754b8490b9be0d8", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De deur staat nog open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "386f96b05a3078c07505b1231944e10cf79659627d8c50e2224f518175032685", "generation_seconds_batch": 15.053585440968163, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.641972541809082, "target_z": 1.6640623468518023, "ce": 6.109982967376709, "genuineness": 3.8546390533447266, "identity": 0.6702315211296082, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/09625cbac6e611b99c0021a884481d7fa334a9d3f01a83b81754b8490b9be0d8.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-0", "key": "0a1816c3f4f7931207a5160358ed02a91ed2d17927f3f8e79da034c6cfb331ef", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La porte est encore ouverte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "296ea71035e602c33567927c0f80f3e0daefba25effa68f1b2835e18c5cbdd2d", "generation_seconds_batch": 17.995810942957178, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.27370595932006836, "target_z": -0.33593747889958164, "ce": 6.173524379730225, "genuineness": 4.519899368286133, "identity": 0.7657080888748169, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/0a1816c3f4f7931207a5160358ed02a91ed2d17927f3f8e79da034c6cfb331ef.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-1", "key": "0a26633c83b43f519702df2041f81ca0f99ec690476d9d2b02404c2fed0f4129", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "142841c9fa52a2d46b96d6695ed1d59addec0b60f764e77d0501f4c052846834", "generation_seconds_batch": 17.66570413496811, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1283485889434814, "target_z": 2.3749998366419227, "ce": 5.657250881195068, "genuineness": 3.6412534713745117, "identity": 0.24812835454940796, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/0a26633c83b43f519702df2041f81ca0f99ec690476d9d2b02404c2fed0f4129.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-0", "key": "0a4071ac03317913a4b3c158d2b8cc1aa7f03ddcfba3e2729c569bc9db194329", "bucket": "emo_Impatience_and_Irritability", "phase": "wording", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La porte est encore ouverte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "9d8846cb17a2af304896b8894907d0d8db134ee933649f119b31f7faf21467fe", "generation_seconds_batch": 14.074501736089587, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21090462803840637, "target_z": -0.42773439422860704, "ce": 5.974957466125488, "genuineness": 4.582659721374512, "identity": 0.5916560888290405, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/0a4071ac03317913a4b3c158d2b8cc1aa7f03ddcfba3e2729c569bc9db194329.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-0", "key": "0a879c599b5768cd240d56c9545776851735b81c755810b901849a708254bdfa", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La porte est encore ouverte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "a751974e3320ab5b22ce8a87fe268865c100738f3f870e64d66af5bcab0547cf", "generation_seconds_batch": 13.625028640963137, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20288744568824768, "target_z": -0.4394531364010325, "ce": 6.165581703186035, "genuineness": 4.68307638168335, "identity": 0.7073805332183838, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/0a879c599b5768cd240d56c9545776851735b81c755810b901849a708254bdfa.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": "0a9ad8a8411c1bb100f55ebbbc213ee71649c02c51db6d127f0ee29c2812f9d2", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "487258cf9fb6d0b5e6e553af8b1c0d5403b04d284c798487b50844c32e89f6b0", "generation_seconds_batch": 14.163754429086111, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0690319538116455, "target_z": 3.749999847532461, "ce": 5.478540420532227, "genuineness": 3.490628719329834, "identity": 0.5479990839958191, "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_Impatience_and_Irritability/0a9ad8a8411c1bb100f55ebbbc213ee71649c02c51db6d127f0ee29c2812f9d2.mp3" }, { "id": "emo_Impatience_and_Irritability-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-0", "key": "0ba1ee39fed9e5e7772e14bfdf247a37457c2a403e9c9e2bcce41f5f1ba0e230", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The door is still open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "dac87e296cda245c15c8ec91364c75528a18e72163e50fb85ed1c044aae4b38f", "generation_seconds_batch": 18.124187557958066, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11336219310760498, "target_z": -0.5703124965967067, "ce": 6.229123115539551, "genuineness": 4.281409740447998, "identity": 0.4777403473854065, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/0ba1ee39fed9e5e7772e14bfdf247a37457c2a403e9c9e2bcce41f5f1ba0e230.mp3" }, { "id": "emo_Impatience_and_Irritability-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-0", "key": "0ba3391b050b79d4d92e27c41ac3c356b4185170992cfc19dc987751ac1df5b1", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La puerta sigue abierta.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "be7f9f51c64dbba276564ddaf3c2481ca0f910f2d78765fb9edb28db04d37716", "generation_seconds_batch": 18.189138951012865, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1759278774261475, "target_z": 3.9062499754962885, "ce": 5.534139156341553, "genuineness": 3.4435582160949707, "identity": 0.7294926643371582, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/0ba3391b050b79d4d92e27c41ac3c356b4185170992cfc19dc987751ac1df5b1.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-1", "key": "0be104a47ccdda722e6de2bd2526fde452441767d19e475087eef450fcc774cd", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cdaeb0275af5d71cd56bb1c5551aa9268023ccaf42863f5c1f2be7d8638f1804", "generation_seconds_batch": 17.920167751028202, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2777145504951477, "target_z": -0.33007810781336894, "ce": 6.006728172302246, "genuineness": 4.532451152801514, "identity": 0.6706550121307373, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/0be104a47ccdda722e6de2bd2526fde452441767d19e475087eef450fcc774cd.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": "0c135c06e1a7200b1303dac9c224d929232879a577f3bbfdc45b6ef644471b26", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I wrote the number on the envelope.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6d30b7e6d2c51d4d073a8cfc8eeddcc0ac7daf4de617cc73a752dec79dfd8133", "generation_seconds_batch": 13.803051889990456, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2624924182891846, "target_z": 1.1093749850255095, "ce": 6.260893821716309, "genuineness": 3.4718005657196045, "identity": 0.33373361825942993, "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_Impatience_and_Irritability/0c135c06e1a7200b1303dac9c224d929232879a577f3bbfdc45b6ef644471b26.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-1", "key": "0c1f99a1b099347000549c305eb7e0d71d549febbfc4c14d2fe22381686b85fe", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "f89e2234c23fdbe4666aa2e22e143bceb446040148d543864c7eeeba1c9ae757", "generation_seconds_batch": 18.884481976972893, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2523267865180969, "target_z": -0.36718748706748555, "ce": 6.133810997009277, "genuineness": 4.20609712600708, "identity": 0.7191323041915894, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/0c1f99a1b099347000549c305eb7e0d71d549febbfc4c14d2fe22381686b85fe.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_Impatience_and_Irritability", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": "662ca476e82fe362d5d35c989e6f5b7f26f0c8fe7ff0f8e74e7d9e5f3c53ee3b", "generation_seconds_batch": 14.175500835990533, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18418067693710327, "target_z": -0.4667968826574099, "ce": 6.0146708488464355, "genuineness": 4.13078498840332, "identity": 0.6017695665359497, "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_Impatience_and_Irritability/0cb70e86df8754d3bba44fe7f798aac7d0ffe2ca68fc75b92ff1a1ed29986ba7.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-1", "key": "0d762914c93e7bb1f6a618404b14a9b18e8f1bfeb7f4fa01376703809f56af0c", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "a52c35678142b8612274915b1b4e737d58274174bb8629b5682e8572a8ece817", "generation_seconds_batch": 17.535330845974386, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6090916395187378, "target_z": 0.15429688810267914, "ce": 6.181467056274414, "genuineness": 4.400654315948486, "identity": 0.41436517238616943, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/0d762914c93e7bb1f6a618404b14a9b18e8f1bfeb7f4fa01376703809f56af0c.mp3" }, { "id": "emo_Impatience_and_Irritability-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-0", "key": "0dbd0b6fcbfd3dffd0496935be715b512c3a0d8b675ab7ded90a2379562efcbc", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La puerta sigue abierta.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "ba21758e5cc89095b7f2e34f10d55f0f941bb99708d5627e437642e60bfdd0e2", "generation_seconds_batch": 18.470272303093225, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6200695037841797, "target_z": 3.0937499373794037, "ce": 5.673136234283447, "genuineness": 3.7918784618377686, "identity": 0.49573516845703125, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/0dbd0b6fcbfd3dffd0496935be715b512c3a0d8b675ab7ded90a2379562efcbc.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": "0dc15c7eb278adcbdcc869a7ec537d3500721adc7f94e1de451995c1538c030f", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "565aa9274be1ec7d9f094169204297604fd83c159d064309f7782cf7f83b3f00", "generation_seconds_batch": 13.690077606006525, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2624924182891846, "target_z": 1.1093749850255095, "ce": 5.847874641418457, "genuineness": 3.9425034523010254, "identity": 0.5335882306098938, "hypothesis": "Ton message est arrivé après mon départ. Je l'ai relu, puis j'ai rangé mon téléphone. Tais-moi quand nous pourrons parler.", "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_Impatience_and_Irritability/0dc15c7eb278adcbdcc869a7ec537d3500721adc7f94e1de451995c1538c030f.mp3" }, { "id": "emo_Impatience_and_Irritability-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-1", "key": "0e88f1c5490b865f9d9e225ed27a06f3abbdac49e61ffeff7513d1fe92277c5d", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I found the little box.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "a79db08432cb1fb0521addd5fce54eea36bffcc678530b879ecfc24bdcc999d7", "generation_seconds_batch": 19.5919619029155, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21624943614006042, "target_z": -0.41992187040555407, "ce": 5.998785495758057, "genuineness": 4.080576419830322, "identity": 0.39204925298690796, "hypothesis": "I found the little box. It was the side. The old window. We can look inside together.", "wer": 0.125, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/0e88f1c5490b865f9d9e225ed27a06f3abbdac49e61ffeff7513d1fe92277c5d.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-0", "key": "0ee1c404eacd7979a49e352f253cf8375fa50464667a63efd67ae7d8ee05330b", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De deur staat nog open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "a104e604f64a7d481e6c79308f52ead470c9646acc3a7e2c3a4193cf08be32f5", "generation_seconds_batch": 20.18019890296273, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4762840270996094, "target_z": 1.4218748924559323, "ce": 5.276002407073975, "genuineness": 3.6663577556610107, "identity": 0.4341905415058136, "hypothesis": "De deur 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_Impatience_and_Irritability/0ee1c404eacd7979a49e352f253cf8375fa50464667a63efd67ae7d8ee05330b.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-0", "key": "0f332e4207669c958c79c531a49ec5f428a0da7fb447fa2316832bb53a602bb8", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De deur staat nog open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dca538bf0ad30a5a3b2f421bdd36d728ec706c3978bee9bdb23a86c619a945b5", "generation_seconds_batch": 18.15530011395458, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2838716506958008, "target_z": 1.1406250803177214, "ce": 5.95112943649292, "genuineness": 3.9299514293670654, "identity": 0.4836963713169098, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/0f332e4207669c958c79c531a49ec5f428a0da7fb447fa2316832bb53a602bb8.mp3" }, { "id": "emo_Impatience_and_Irritability-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-1", "key": "0f72dbe70325097bdd8ac19685569fa5abebc12c7d708e2364ff3a554310e31d", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "09ee56909d4e141bbd06210c9052db6c445153f7572b94ca813157d942deacc9", "generation_seconds_batch": 18.6792921340093, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18952548503875732, "target_z": -0.4589843588343569, "ce": 6.117925643920898, "genuineness": 4.287685871124268, "identity": 0.7038387656211853, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/0f72dbe70325097bdd8ac19685569fa5abebc12c7d708e2364ff3a554310e31d.mp3" }, { "id": "emo_Impatience_and_Irritability-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-1", "key": "0fc04fbf350d1625c2dc8aef171f93f02a67114cd08c6af02a3ae23388a7e99c", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "707893bc32ffaa1d9b51421fcd2cdfba0543bd3ddd560747d831eaa0afa8819d", "generation_seconds_batch": 14.061288948985748, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.740039050579071, "target_z": 0.3457031554594749, "ce": 6.125868320465088, "genuineness": 3.7416701316833496, "identity": 0.6542345285415649, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem Alten entschacht. 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_Impatience_and_Irritability/0fc04fbf350d1625c2dc8aef171f93f02a67114cd08c6af02a3ae23388a7e99c.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-1", "key": "1049873e938acd40a269c4a95c175e41a10e797fe323536be2e9ebe027b5607f", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "0d781b93d71b3904a6147f94739d541b4e00cdd3346364a706680476035501a3", "generation_seconds_batch": 13.34224573103711, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.32715386152267456, "target_z": -0.257812502041976, "ce": 5.9431867599487305, "genuineness": 4.149612903594971, "identity": 0.5592992305755615, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/1049873e938acd40a269c4a95c175e41a10e797fe323536be2e9ebe027b5607f.mp3" }, { "id": "emo_Impatience_and_Irritability-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-1", "key": "11743a7cd1eeaac3f553676299c37c5f0b2a68a6dbca3f94797f63a6b969d4eb", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] He encontrado la cajita.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "b55d5d6eaa96dc6c1c5f941f294c2496b381049f951fb8a38ed0293109daca29", "generation_seconds_batch": 17.819966171053238, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08663824200630188, "target_z": -0.6093749850255096, "ce": 6.022613525390625, "genuineness": 4.632867813110352, "identity": 0.41366830468177795, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/11743a7cd1eeaac3f553676299c37c5f0b2a68a6dbca3f94797f63a6b969d4eb.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": "123d9beee1a38de0ff760b36c618dfa8374102f0f570d431a92da0d9fd486f61", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Escribí el número en el sobre.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "512ff9085648c3e4c4f6e81c194481c729f85cf458c20f9bd76994662d1a50c2", "generation_seconds_batch": 13.65558570495341, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7381789684295654, "target_z": 1.8046876014181399, "ce": 5.4944257736206055, "genuineness": 3.810706615447998, "identity": 0.6471642255783081, "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_Impatience_and_Irritability/123d9beee1a38de0ff760b36c618dfa8374102f0f570d431a92da0d9fd486f61.mp3" }, { "id": "emo_Impatience_and_Irritability-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-0", "key": "1246eac062de55f9b8fc9d69e0a94a7053cef60577a2bd2cd1cec6512d9fa187", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The door is still open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "14874f19b42f1768c1518eff39ad3d6a4c590cb56afaff3e95c5e6e093b70279", "generation_seconds_batch": 17.894780700909905, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13474136590957642, "target_z": -0.5390624884288029, "ce": 6.252951145172119, "genuineness": 3.860914945602417, "identity": 0.1834769994020462, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/1246eac062de55f9b8fc9d69e0a94a7053cef60577a2bd2cd1cec6512d9fa187.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-0", "key": "1266e7caf7233e23939fb37ce4ff1de48cdaa8fec1e81d4b9038ed61b1ba5113", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De deur staat nog open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "5672386863802dc1e4b69c455b00faf8acd6cdfe0463dc3e9fb07f057b4b623c", "generation_seconds_batch": 19.812315721064806, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8450746536254883, "target_z": 1.9609373808847352, "ce": 5.903473377227783, "genuineness": 3.9927117824554443, "identity": 0.39046329259872437, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/1266e7caf7233e23939fb37ce4ff1de48cdaa8fec1e81d4b9038ed61b1ba5113.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_Impatience_and_Irritability", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": "38f869ee838ab2cb3b534e6487bda27484f69946dfcf6b32631affbdcd868af8", "generation_seconds_batch": 13.278927120030858, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.046552300453186035, "target_z": -0.6679687394497908, "ce": 6.157639026641846, "genuineness": 4.168440818786621, "identity": 0.6179437041282654, "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_Impatience_and_Irritability/12a7b850c68b1e935d69d2b179f3c0df54c4775061935760902fd9f6cbfc7541.mp3" }, { "id": "emo_Impatience_and_Irritability-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-0", "key": "12b457dea9d314ea6ddf9acf57efc3bc9335ae9b5d78a68321b0fd467013b3dd", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La puerta sigue abierta.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "4a5fcdd09bf1054440d575f3299698c33f658afe89090b7c09095aaad7b0e6f2", "generation_seconds_batch": 18.192877508932725, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11870697140693665, "target_z": -0.5625000163358077, "ce": 5.808161735534668, "genuineness": 4.337893962860107, "identity": 0.5534441471099854, "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_Impatience_and_Irritability/12b457dea9d314ea6ddf9acf57efc3bc9335ae9b5d78a68321b0fd467013b3dd.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-1", "key": "1378270180b962295cb8bcc31001720cb4b1717ba2693ee7352f9fae056ad720", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "d4e68bd3250b2d1cd4cad5b6cc477dc4c546455730de8897ab8dec52ef8e57c3", "generation_seconds_batch": 18.035692835925147, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16146531701087952, "target_z": -0.5, "ce": 6.316492557525635, "genuineness": 4.394378662109375, "identity": 0.5560064911842346, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/1378270180b962295cb8bcc31001720cb4b1717ba2693ee7352f9fae056ad720.mp3" }, { "id": "emo_Impatience_and_Irritability-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-0", "key": "13f5dba7080ff8b86966ad549fe4bc4399410f64c30831ae4d6519581c680844", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The door is still open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "076846e4a4bfa6ab2de2ada081ad749b3eea8ef94ee04b1e3083fc7deff593ce", "generation_seconds_batch": 18.098767507006414, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0861142873764038, "target_z": 0.8515624829835335, "ce": 5.8875885009765625, "genuineness": 3.4372823238372803, "identity": 0.4798770546913147, "hypothesis": "The 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_Impatience_and_Irritability/13f5dba7080ff8b86966ad549fe4bc4399410f64c30831ae4d6519581c680844.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": "140b5be7cbec6bd9812148e56f68cfb92c8e697c647f73f36ea2c258c3a5801d", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "a407251dea19c301528b434a2c9423bfda7aff9ec80cede963f34a6979bea7bc", "generation_seconds_batch": 15.048688951996155, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9311153292655945, "target_z": 0.6249999891094615, "ce": 6.229123115539551, "genuineness": 4.118232727050781, "identity": 0.5547527074813843, "hypothesis": "Si un mensaje llegó después de que me fuera, lo leí dos veces y guardé el teléfono. Dime cuándo podemos hablar.", "wer": 0.1, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/140b5be7cbec6bd9812148e56f68cfb92c8e697c647f73f36ea2c258c3a5801d.mp3" }, { "id": "emo_Impatience_and_Irritability-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-0", "key": "142939b1c1ac56f72871a114e2dfe93b098b32010fccaf9bbddc4b0c9bb965b5", "bucket": "emo_Impatience_and_Irritability", "phase": "wording", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Tür ist noch offen.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "de9559c6bacef7d2f914f9008f50644e0c51de0db72efcb10e176cd0c6329249", "generation_seconds_batch": 14.320809809025377, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14008614420890808, "target_z": -0.5312500081679039, "ce": 6.157639026641846, "genuineness": 4.394378662109375, "identity": 0.46443453431129456, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/142939b1c1ac56f72871a114e2dfe93b098b32010fccaf9bbddc4b0c9bb965b5.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-0", "key": "142f658968cdecb1d890cb944847c45da3fc744bd0eab41c8c0318bab139123e", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De deur staat nog open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "ee35da7ddc2df529362be7ecb85fe200ba64798211ee5eccde76218dfe5a767d", "generation_seconds_batch": 18.54262054199353, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.096803903579712, "target_z": 0.8671875306296395, "ce": 5.990842819213867, "genuineness": 4.036643981933594, "identity": 0.5603435039520264, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/142f658968cdecb1d890cb944847c45da3fc744bd0eab41c8c0318bab139123e.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": "143540ba379d34a2223e09b0bf58904b72b25af49c2dbcf6beff9bff78022eaa", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "584b3b7231c285c1f8fef5a49ed65ebd637a35f2831720b047bfa9d28b3689c9", "generation_seconds_batch": 18.41066536400467, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.171107053756714, "target_z": 2.437500027226346, "ce": 5.935244083404541, "genuineness": 3.8671910762786865, "identity": 0.5046858787536621, "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_Impatience_and_Irritability/143540ba379d34a2223e09b0bf58904b72b25af49c2dbcf6beff9bff78022eaa.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-0", "key": "143a300465caae8e48d5e6fa8e3c137f9d8ceee9f0e691dc5f5a12036c1c3a64", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De deur staat nog open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "ddbc808ab521e96dae1cb4fa0df6befcff761eb632ef57247ebca480d624c055", "generation_seconds_batch": 17.884217155049555, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3533539772033691, "target_z": 1.242187628644486, "ce": 6.062326908111572, "genuineness": 3.8169827461242676, "identity": 0.4150351881980896, "hypothesis": "De deur staat nog open. Ik heb je je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/143a300465caae8e48d5e6fa8e3c137f9d8ceee9f0e691dc5f5a12036c1c3a64.mp3" }, { "id": "emo_Impatience_and_Irritability-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-1", "key": "14eca405693d985a400d043c760ff4d9fc1589505f11434b03598fe1c9aeb390", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I found the little box.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "2a8309b0287212a35ec29d012fda44870ecdd57318af7fd14be398d38512e5ba", "generation_seconds_batch": 13.142973654088564, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.027845531702041626, "target_z": -0.6953124857061682, "ce": 6.221180438995361, "genuineness": 4.419482707977295, "identity": 0.4961155354976654, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/14eca405693d985a400d043c760ff4d9fc1589505f11434b03598fe1c9aeb390.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": "15047f724880dbab442856bafc2ba8cba42b50ed9c0ceda6d1ee4b8b499d0beb", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "afd5b96a2c4e9bc21f6b78192be8ab120c3a0a09848267acc4f40e4ae41f0e3b", "generation_seconds_batch": 15.408313142019324, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.187665343284607, "target_z": 1.0, "ce": 5.967014789581299, "genuineness": 3.7040140628814697, "identity": 0.3922399878501892, "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_Impatience_and_Irritability/15047f724880dbab442856bafc2ba8cba42b50ed9c0ceda6d1ee4b8b499d0beb.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_Impatience_and_Irritability", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": "4486860c1bb09cd4c14f3d4f8137a1a2c58c6ef1af6bcccede9f5a9b1a1f7d2c", "generation_seconds_batch": 14.72581505193375, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18952548503875732, "target_z": -0.4589843588343569, "ce": 6.221180438995361, "genuineness": 4.570107460021973, "identity": 0.47117117047309875, "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_Impatience_and_Irritability/15585f3962d31fd159bb39a755593ab24aa0df87e4725d7772f40811258760f5.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-1", "key": "159546a9aa0f10a4f31244a9ec107c9be948fa9bbbe96ae11702f4a439e0ddfc", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "6c42f1b53302b5fed00a5183291d7f0e4ef99a6224378e01f55a08e8bef39699", "generation_seconds_batch": 18.228360436973162, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6271302700042725, "target_z": 0.1806640144284824, "ce": 6.117925643920898, "genuineness": 4.18099308013916, "identity": 0.49809104204177856, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/159546a9aa0f10a4f31244a9ec107c9be948fa9bbbe96ae11702f4a439e0ddfc.mp3" }, { "id": "emo_Impatience_and_Irritability-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-1", "key": "15e9d8948325b81625f7cd673e8666d5ec91e17c927b4243ab779301a03dda38", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I found the little box.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "95a1df3c1de2ccf5d6dfa2b7b4faf1e5043bb5a9f5746885f6358a0b4f517fbe", "generation_seconds_batch": 13.218400561949238, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0973278284072876, "target_z": -0.5937499809415576, "ce": 5.704906940460205, "genuineness": 3.6663577556610107, "identity": 0.28722983598709106, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/15e9d8948325b81625f7cd673e8666d5ec91e17c927b4243ab779301a03dda38.mp3" }, { "id": "emo_Impatience_and_Irritability-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-0", "key": "1611227a7542d242e67ad05f47c59623fd61577ff08933cf8f3dbc43d062a8c0", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Tür ist noch offen.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "5521ff0337c515890596716211aee045f7dc1118faf63135fb0b1a091d9204bc", "generation_seconds_batch": 14.235988761065528, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7381789684295654, "target_z": 1.8046876014181399, "ce": 6.157639026641846, "genuineness": 4.519899368286133, "identity": 0.35584455728530884, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/1611227a7542d242e67ad05f47c59623fd61577ff08933cf8f3dbc43d062a8c0.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-0", "key": "163b909fb8894b4efa404ea3292af9ea76679334a5805c2d85dc619796653b84", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De deur staat nog open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "00a13b34c8ab95294c367f24c9fa0ebbd3a940204945928808a7a7d3ac710952", "generation_seconds_batch": 18.29708983609453, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0700799226760864, "target_z": 0.8281249986386827, "ce": 5.990842819213867, "genuineness": 4.281409740447998, "identity": 0.7522401809692383, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/163b909fb8894b4efa404ea3292af9ea76679334a5805c2d85dc619796653b84.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": "16fa2ddb9018d155fc1a19b619bd39d32ff3d4f8abeb6cd2a72ae1c44156b762", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a42f9429e92147fcf80672abbbe9d2138c246623cc001a4019b385d17de4cc7d", "generation_seconds_batch": 21.65155936498195, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3848986625671387, "target_z": 2.749999934656769, "ce": 5.055593490600586, "genuineness": 3.4498343467712402, "identity": -0.09721348434686661, "hypothesis": "Jemand hat den kleinen blauen Stuhl umgestellt. Er stand hier neben dem hohen Bücherregal. Wir stellen ihn noch dem Essen zurück.", "wer": 0.047619047619047616, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/16fa2ddb9018d155fc1a19b619bd39d32ff3d4f8abeb6cd2a72ae1c44156b762.mp3" }, { "id": "emo_Impatience_and_Irritability-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-0", "key": "170a217d7e21090232ec1b1067d7890a36d5f8253d6290a92db09fe6788b6b3d", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Tür ist noch offen.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "cebcaa28d11a7b134647fd71606bf7d9aa59e413ee241395be1ff87d01c1969d", "generation_seconds_batch": 17.869783257017843, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7542133331298828, "target_z": 1.8281250857629907, "ce": 5.935244083404541, "genuineness": 4.545003414154053, "identity": 0.4820108711719513, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/170a217d7e21090232ec1b1067d7890a36d5f8253d6290a92db09fe6788b6b3d.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": "174fbc3662334d731fdcc20f8b5469a676a82ecb64f837ba4d3609df8dc3fb60", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "8df3032c5867210104a3cac2e951b6dcb43ac604832afc1d21c8627ce1f62c30", "generation_seconds_batch": 13.016488951048814, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3100717067718506, "target_z": 2.6406251238798752, "ce": 5.919358730316162, "genuineness": 3.7416701316833496, "identity": 0.7006742358207703, "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_Impatience_and_Irritability/174fbc3662334d731fdcc20f8b5469a676a82ecb64f837ba4d3609df8dc3fb60.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-1", "key": "176566091d42ebfac8a7385fbc1a26554e74ee378c52b814419f4a992dd9efde", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "9dde0e2461eea504458eb4b75bee55ffeec73b6f39817e8f07e8e67f9f7b6603", "generation_seconds_batch": 18.001885836943984, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0011215806007385254, "target_z": -0.7343749741349711, "ce": 6.2767791748046875, "genuineness": 4.607763767242432, "identity": 0.7230356931686401, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/176566091d42ebfac8a7385fbc1a26554e74ee378c52b814419f4a992dd9efde.mp3" }, { "id": "emo_Impatience_and_Irritability-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-0", "key": "18c537372df228c343b4331799881433d36dba94964546a5ed2e5f535d8ced70", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The door is still open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "faa006e84bc81b5f29f6836bcacacadb3d88fb9bc39deb9994f4f84a9a2568f4", "generation_seconds_batch": 17.956502715009265, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5938694477081299, "target_z": 1.5937498938172496, "ce": 6.1020402908325195, "genuineness": 3.7793264389038086, "identity": 0.5550280809402466, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/18c537372df228c343b4331799881433d36dba94964546a5ed2e5f535d8ced70.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-0", "key": "1938c1206716038d008ae04d0e780e3e8963adfca60c976a078002fa4a5c399a", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La porte est encore ouverte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "6d3926ffc3029d6e3361d561dee3d0abb0ddb5d416dc1c4a31bdcbdbc1f01871", "generation_seconds_batch": 17.8829025629675, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3111194968223572, "target_z": -0.28124998638682686, "ce": 5.831989288330078, "genuineness": 4.2374773025512695, "identity": 0.6157100200653076, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/1938c1206716038d008ae04d0e780e3e8963adfca60c976a078002fa4a5c399a.mp3" }, { "id": "emo_Impatience_and_Irritability-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-1", "key": "194d30b0d23b811cb4c206c1d5075a4e70030d3e4b0b3f26515de903a0881470", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "1481f266cdc83b0109b7cb7190fa274787fb122770c05b8704da48d89d2c8196", "generation_seconds_batch": 18.102000265964307, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.116034597158432, "target_z": -0.5664062346851803, "ce": 6.1894097328186035, "genuineness": 4.482243061065674, "identity": 0.7212233543395996, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/194d30b0d23b811cb4c206c1d5075a4e70030d3e4b0b3f26515de903a0881470.mp3" }, { "id": "emo_Impatience_and_Irritability-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-1", "key": "1a172fbf0aa4dbd331a424fec493b87aebb7f87476449d8bdf4f419742ad2c3c", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] He encontrado la cajita.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "d4821d9f561226cb132a8b8bb3ffc388c8f4ba7b20ff5a07c776f1f019bb48c7", "generation_seconds_batch": 18.34630965802353, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4762840270996094, "target_z": 1.4218748924559323, "ce": 5.307773113250732, "genuineness": 3.487490653991699, "identity": 0.3745250999927521, "hypothesis": "He encontrado la cajita. Estaba junto. Vamos a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.058823529411764705, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/1a172fbf0aa4dbd331a424fec493b87aebb7f87476449d8bdf4f419742ad2c3c.mp3" }, { "id": "emo_Impatience_and_Irritability-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-0", "key": "1a5a2b6454211ae0a7c80d2bec326d0e348841c6298c5b0c4e2ea33d2830cd5a", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Tür ist noch offen.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "33a65ba02ed43a7d9a05c49cd2b1e2a80c2e01d10f52431b57ead6bf540b0872", "generation_seconds_batch": 17.890652947011404, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2828235626220703, "target_z": 4.062499754962884, "ce": 6.070269584655762, "genuineness": 3.8546390533447266, "identity": 0.46349287033081055, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/1a5a2b6454211ae0a7c80d2bec326d0e348841c6298c5b0c4e2ea33d2830cd5a.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": "1a5d2fcdea5b5030d6a82e31562181cd35e75f64d7c130bbfe6633d9446a6ddc", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I wrote the number on the envelope.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "42ca311e32ac75d401f6df9c4e4075016e4fa2af2bbe50ac9851334b50f57cf0", "generation_seconds_batch": 18.294561796006747, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9257705211639404, "target_z": 0.6171874652864086, "ce": 5.879645347595215, "genuineness": 3.1987926959991455, "identity": 0.3371965289115906, "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_Impatience_and_Irritability/1a5d2fcdea5b5030d6a82e31562181cd35e75f64d7c130bbfe6633d9446a6ddc.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-0", "key": "1abbbd7e4936a09498b5291b0f9cd086299cf9c352eeec37dc62cd392668b853", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La porte est encore ouverte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "fee013001679bf6be845420a491dfe6d7e600c6d8e564f0ee611e4cac2e1236b", "generation_seconds_batch": 15.539749585906975, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8389176726341248, "target_z": 0.4902343670022608, "ce": 5.998785495758057, "genuineness": 4.218649387359619, "identity": 0.5677366256713867, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt ?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/1abbbd7e4936a09498b5291b0f9cd086299cf9c352eeec37dc62cd392668b853.mp3" }, { "id": "emo_Impatience_and_Irritability-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-0", "key": "1bc4db8fe926cb38085232c50c9fe82bdc4b049a6d38c180c98c0ddac1428809", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Tür ist noch offen.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "0e677a98721a23005a9913245b0ca57e01c230dc6d8e7f78ffb0aed9d23c1e78", "generation_seconds_batch": 13.337640649056993, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4901700019836426, "target_z": -0.01953126599547842, "ce": 6.0305562019348145, "genuineness": 4.243753433227539, "identity": 0.5586268901824951, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/1bc4db8fe926cb38085232c50c9fe82bdc4b049a6d38c180c98c0ddac1428809.mp3" }, { "id": "emo_Impatience_and_Irritability-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-1", "key": "1c31184f14537d3f356acf686b941a1a634a5ceef656ac5abb87b1c8dcdc6bdf", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] He encontrado la cajita.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "cdce267d7d5cc933f216e342205d8e11b31c999965785d82b1405c1cd3fc9db9", "generation_seconds_batch": 18.338985887006857, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16413772106170654, "target_z": -0.4960937380884735, "ce": 6.173524379730225, "genuineness": 4.68307638168335, "identity": 0.7029224038124084, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/1c31184f14537d3f356acf686b941a1a634a5ceef656ac5abb87b1c8dcdc6bdf.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-0", "key": "1c66b9a688a3aba8252ee90a55bef21b280886844242da7c9c7ca10a20f10070", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La porte est encore ouverte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "489ea63cdc94c27bd80e0416baa4c2a866a215a040946b84fd307e6077bdc6b1", "generation_seconds_batch": 19.844728477066383, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9786944389343262, "target_z": 2.1562498665909033, "ce": 6.006728172302246, "genuineness": 4.093128204345703, "identity": 0.726926863193512, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/1c66b9a688a3aba8252ee90a55bef21b280886844242da7c9c7ca10a20f10070.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-1", "key": "1c9e461e843e1856415b92fb475e8562b2f87d264c6b8d2f79917a32739c7cf3", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "08548e796b07d3b405c348b19d850a4eb6f67f4f461fae2085beb1dfa0988ea8", "generation_seconds_batch": 13.193839124054648, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.28840410709381104, "target_z": -0.314453147291571, "ce": 5.998785495758057, "genuineness": 4.218649387359619, "identity": 0.36753594875335693, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/1c9e461e843e1856415b92fb475e8562b2f87d264c6b8d2f79917a32739c7cf3.mp3" }, { "id": "emo_Impatience_and_Irritability-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-1", "key": "1d268c21e2ceaf81fa9ea1334295da95d8ceaa5e1b49138441380e3fd5328472", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] He encontrado la cajita.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "33abbc47d5ca9355247cd1c7a52eeaf7d69a2c11879f9096658938ef7fd9b5a0", "generation_seconds_batch": 18.01843875797931, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.027845531702041626, "target_z": -0.6953124857061682, "ce": 6.173524379730225, "genuineness": 4.457139015197754, "identity": 0.691959798336029, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/1d268c21e2ceaf81fa9ea1334295da95d8ceaa5e1b49138441380e3fd5328472.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_Impatience_and_Irritability", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": "895334938bbab08092ade68f41ced513c9cbb735732d6be03cde02c3da6e1e49", "generation_seconds_batch": 14.750783954979852, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10801738500595093, "target_z": -0.5781250204197597, "ce": 6.133810997009277, "genuineness": 4.256305694580078, "identity": 0.6497046947479248, "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_Impatience_and_Irritability/1d559e6da25f8bbacc3b53d5880369445633ce7ab0125ca7b07093108b8c8de3.mp3" }, { "id": "emo_Impatience_and_Irritability-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-1", "key": "1d6dd275bc22df06d4682baa6d174a1f8279a0697c3b8ecd09e196222a0a17ff", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "752b3a4058d8381a09ff4da8894916dc2ab2797043726e7c61849dfb21711be3", "generation_seconds_batch": 13.057030930067413, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.017155945301055908, "target_z": -0.7109374897901202, "ce": 6.348263263702393, "genuineness": 4.20609712600708, "identity": 0.3452141284942627, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/1d6dd275bc22df06d4682baa6d174a1f8279a0697c3b8ecd09e196222a0a17ff.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-0", "key": "1d78a79fb50649e572fd79062ad137297ae7f3d9092242235a212c51d5eb8b60", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La porte est encore ouverte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "396bbcaab6a362fd5ebab2ed0b9538129428cd4e8f0de40b19cf8ce79d01d3e7", "generation_seconds_batch": 20.048168768989854, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.813529908657074, "target_z": 0.4531249877481442, "ce": 6.038498878479004, "genuineness": 4.319066047668457, "identity": 0.6319727301597595, "hypothesis": "La porte est encore ouverte. Je posais ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.1111111111111111, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/1d78a79fb50649e572fd79062ad137297ae7f3d9092242235a212c51d5eb8b60.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_Impatience_and_Irritability", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": "0d7fb52a0463309afbeac5ef9a628680d1bd73882f497de17f345f1afcbc74ab", "generation_seconds_batch": 13.245083724032156, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1868530809879303, "target_z": -0.4628906207458834, "ce": 6.23706579208374, "genuineness": 4.369274139404297, "identity": 0.45215824246406555, "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_Impatience_and_Irritability/1d829402ab2176d2024ae3e918286a39ec094d9a5299caa0e048ba37912e1579.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-1", "key": "1d82af0e2df6a64ed6333e6f44081bfd06e244bf4a6d5c101be43009f5f2d738", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "0a2e8994a986adbd091ae6d2b4a5b27a310aeb989a2dbb4e04a4dcedcdc03b19", "generation_seconds_batch": 19.235095151001588, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3533539772033691, "target_z": 1.242187628644486, "ce": 6.062326908111572, "genuineness": 3.8420867919921875, "identity": 0.41941285133361816, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/1d82af0e2df6a64ed6333e6f44081bfd06e244bf4a6d5c101be43009f5f2d738.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-0", "key": "1daa10e54615fc474329f73eae186d5afe0adf6ea2c264e6b62281b3383d31e8", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La porte est encore ouverte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "29cfcf193a61d1d87f65a5056cf7536a604f7da65b59947ef821541e8b5f6efd", "generation_seconds_batch": 19.052202227991074, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3586986064910889, "target_z": 1.249999891094615, "ce": 5.927301406860352, "genuineness": 3.998987913131714, "identity": 0.7056291103363037, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/1daa10e54615fc474329f73eae186d5afe0adf6ea2c264e6b62281b3383d31e8.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": "1e72904b1f2012e9e0e7edc27a0efc514a57ec86dc666a28ae837f8d491f449a", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The keys are on the kitchen table.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "072e7a02fedde47bd44532daa9985ce15240c1ddb5330ee4f3905ac73ace51a5", "generation_seconds_batch": 15.550357042928226, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4313772916793823, "target_z": -0.10546876667613708, "ce": 5.982900142669678, "genuineness": 3.8420867919921875, "identity": 0.4060913920402527, "hypothesis": "The keys are on the kitchen table. I check the drawer, then look beside the window. Take them with you when you leave.", "wer": 0.08695652173913043, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/1e72904b1f2012e9e0e7edc27a0efc514a57ec86dc666a28ae837f8d491f449a.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_Impatience_and_Irritability", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": "faef226481e17cc166dcea7fc64f6d50fd11d3dbaba54552735390053592b621", "generation_seconds_batch": 14.750783954979852, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11068978905677795, "target_z": -0.5742187585082332, "ce": 6.229123115539551, "genuineness": 3.9927117824554443, "identity": 0.514860987663269, "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_Impatience_and_Irritability/1eaf0e0e2c966186cf6ada2de41819a315f8b1b1eeeeef5a84a28dd582998db8.mp3" }, { "id": "emo_Impatience_and_Irritability-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-1", "key": "1f37c3ddb6e183130eab4ab2b4446a03e772f0b59344a96874949aae756d6006", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] He encontrado la cajita.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "0a2e56da20ebe3dde1cea462a69808306c9f95edf5c36a685f3e0d8443ac695c", "generation_seconds_batch": 19.14660694799386, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6237897872924805, "target_z": 0.1757812197106898, "ce": 5.442798614501953, "genuineness": 3.7416701316833496, "identity": 0.54719078540802, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/1f37c3ddb6e183130eab4ab2b4446a03e772f0b59344a96874949aae756d6006.mp3" }, { "id": "emo_Impatience_and_Irritability-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-0", "key": "1f7dc4cff9cb8ae183d64bae4fcc75130476fe0c4c48daf72a203724cdfb70ff", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La puerta sigue abierta.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "73238ebf527f299fa253221477f926d0254f2aab23701cc5a5dfbb498ae34bc8", "generation_seconds_batch": 18.05922950198874, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8990465998649597, "target_z": 0.5781250204197597, "ce": 5.462655067443848, "genuineness": 3.8420867919921875, "identity": 0.5381109714508057, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/1f7dc4cff9cb8ae183d64bae4fcc75130476fe0c4c48daf72a203724cdfb70ff.mp3" }, { "id": "emo_Impatience_and_Irritability-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-0", "key": "1f9c24dc19eda900014456f6b9780bba8bece79aaf096e97e4414f99cf628c2e", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Tür ist noch offen.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "8ba01aeec142eb22bc9bd4aa26bf8671d64f5f122f8f59f8429117e55823f54a", "generation_seconds_batch": 18.390069631976075, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2036997079849243, "target_z": 1.0234374843448508, "ce": 6.252951145172119, "genuineness": 4.557555198669434, "identity": 0.7222726345062256, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/1f9c24dc19eda900014456f6b9780bba8bece79aaf096e97e4414f99cf628c2e.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": "1feb24aa941eda5554c28dcb40a1d28daa511228c1b16cea3f1ee345dc534f3b", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Escribí el número en el sobre.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c183be9770b19d6831bca78442d0b9e2dc440390918f01932e791a1efbc2380b", "generation_seconds_batch": 18.65110465104226, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0749008655548096, "target_z": 2.2968751211572407, "ce": 5.166790962219238, "genuineness": 3.672633647918701, "identity": 0.6500188112258911, "hypothesis": "Escribí el número en el sobre y comprueba las dos últimas cifras. Llámame cuando tengas un momento.", "wer": 0.10526315789473684, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/1feb24aa941eda5554c28dcb40a1d28daa511228c1b16cea3f1ee345dc534f3b.mp3" }, { "id": "emo_Impatience_and_Irritability-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-0", "key": "1ff89b3b55425a1c473460f35f83967a375a5626aca2094ce20692ea5bff7f48", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La puerta sigue abierta.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "f79add46dc9ee3ac96d5bd786a2ed5ef5c56303c340922e9ed77c459730117f9", "generation_seconds_batch": 18.175981712993234, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4126705229282379, "target_z": -0.13281251293251448, "ce": 5.855817794799805, "genuineness": 4.093128204345703, "identity": 0.5450867414474487, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/1ff89b3b55425a1c473460f35f83967a375a5626aca2094ce20692ea5bff7f48.mp3" }, { "id": "emo_Impatience_and_Irritability-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-0", "key": "201f1957560771ce02220581e6a6d5def0efe613894d65cfebb1480f25cb0559", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Tür ist noch offen.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "7c84532f1a83622e1bb160017f70610d775cbbecd098e81a909c701758a1b660", "generation_seconds_batch": 19.554461485007778, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6545223593711853, "target_z": 0.22070312278785936, "ce": 6.062326908111572, "genuineness": 4.281409740447998, "identity": 0.5376759171485901, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/201f1957560771ce02220581e6a6d5def0efe613894d65cfebb1480f25cb0559.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": "202358f1b3a15d0f3420632dfcdfec6ad20c479d02d567f5fec4251b2aa5ddcd", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a57fe00bcd67295dcb240663e8803715772de587ac9dddfb866d7b133aa6d574", "generation_seconds_batch": 16.803322314983234, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5083527565002441, "target_z": 1.4687498611456342, "ce": 6.340320587158203, "genuineness": 3.8044304847717285, "identity": 0.39423105120658875, "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_Impatience_and_Irritability/202358f1b3a15d0f3420632dfcdfec6ad20c479d02d567f5fec4251b2aa5ddcd.mp3" }, { "id": "emo_Impatience_and_Irritability-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-0", "key": "20718b59936f2ffe1e93bfad74b474f59f3c24ebc3af732066e68291627a667c", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Tür ist noch offen.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "aafb177cf63a2521d9b02e4612295dfcd9697b0a7154bc536ceb846a97aa91c9", "generation_seconds_batch": 19.286862999084406, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.41868340969085693, "target_z": -0.12402345630319538, "ce": 6.149696350097656, "genuineness": 4.7834930419921875, "identity": 0.6185626983642578, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/20718b59936f2ffe1e93bfad74b474f59f3c24ebc3af732066e68291627a667c.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-0", "key": "2117a82a29fd37aee9a23f364952922d720c36ac127d2238da22078c84120e53", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De deur staat nog open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "9f822cdf365fb7ff7ecae3a7bc594831f91ffd6a6a1aa05032599e9fb0644068", "generation_seconds_batch": 17.730114877107553, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2304236888885498, "target_z": 1.0625000163358078, "ce": 6.070269584655762, "genuineness": 4.268857479095459, "identity": 0.5737125873565674, "hypothesis": "De deur 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_Impatience_and_Irritability/2117a82a29fd37aee9a23f364952922d720c36ac127d2238da22078c84120e53.mp3" }, { "id": "emo_Impatience_and_Irritability-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-1", "key": "217732e6eb3e565a2c388b2a8a694b9d43fb26f795bf1e48119583d4cb697cbe", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] He encontrado la cajita.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "3ec7947907b50966d1b6dd0a3cd2a07fe1ab4aa11b71cda7e0da2135c69387a6", "generation_seconds_batch": 20.157502248999663, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5275835394859314, "target_z": 0.03515622651727636, "ce": 5.25614595413208, "genuineness": 3.5816311836242676, "identity": 0.324804425239563, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/217732e6eb3e565a2c388b2a8a694b9d43fb26f795bf1e48119583d4cb697cbe.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-1", "key": "217d52f366236e34f9bc09bd09f12d01ab3fbbfe453e08d6d69c3a5fac683a4a", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "cfabdfcd8910c3bc55f12bfb11ab0787816787066b0fe3b0a0ee0c5f26d91927", "generation_seconds_batch": 18.37529989297036, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9872356653213501, "target_z": 0.7070312714407476, "ce": 5.974957466125488, "genuineness": 4.15588903427124, "identity": 0.37594810128211975, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/217d52f366236e34f9bc09bd09f12d01ab3fbbfe453e08d6d69c3a5fac683a4a.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": "21ad4b6436ab0c082f907c99de1b3c2b7b108a3fc1236119a4bc4554d787eac6", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Your message arrived after I had left.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "855a9c2d08e9458523ada23cd2aeda80b5a628c652b5d03c11d5eafa25d68bf8", "generation_seconds_batch": 19.393966111936606, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2886924743652344, "target_z": 2.6093750285876633, "ce": 5.7128496170043945, "genuineness": 3.6287014484405518, "identity": 0.3539057970046997, "hypothesis": "Your message arrived after I had left. I've read it twice before putting the phone away. Let me know when 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_Impatience_and_Irritability/21ad4b6436ab0c082f907c99de1b3c2b7b108a3fc1236119a4bc4554d787eac6.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-1", "key": "21f1753796333515cfcd53fb88c93c719380652a8027fd953e6a3fde4b9f6bfd", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "96727fec6003d2ce1d3d1ee8791455d4c359ee7d81e9cac4d89f90abff702e9a", "generation_seconds_batch": 17.937514627934434, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24564579129219055, "target_z": -0.37695312006522474, "ce": 6.141753673553467, "genuineness": 4.7332844734191895, "identity": 0.7415385842323303, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/21f1753796333515cfcd53fb88c93c719380652a8027fd953e6a3fde4b9f6bfd.mp3" }, { "id": "emo_Impatience_and_Irritability-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-0", "key": "226f13f7cce1fdbf36608545abc35c5735094e9c0ba312dc06241efb82fea087", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The door is still open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "f22b121a2a2726a12939d8dae7e35e5a48836e19b97b24cbed7441a8e634a66f", "generation_seconds_batch": 13.42370345001109, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18017208576202393, "target_z": -0.47265625374362263, "ce": 6.141753673553467, "genuineness": 4.262581825256348, "identity": 0.31117507815361023, "hypothesis": "The door is still open. I'd put your coat on the chair. Tell me when you are ready.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/226f13f7cce1fdbf36608545abc35c5735094e9c0ba312dc06241efb82fea087.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-0", "key": "22c53d638e97b0ed6312797c8f3998cdde2a925c4f0719fc3de9a0904778abf4", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De deur staat nog open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "93711527551c62a12d917b54a52a00aad449b17ae975d0879046e03866e8fbe2", "generation_seconds_batch": 18.75419270596467, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5629928112030029, "target_z": 0.08691407704907878, "ce": 6.141753673553467, "genuineness": 4.419482707977295, "identity": 0.5432413816452026, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/22c53d638e97b0ed6312797c8f3998cdde2a925c4f0719fc3de9a0904778abf4.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": "22fe3709574023e51ba17aeed10ad15dcfc7c62bf31ef35ebeea75aa427056b9", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "89147a2e0cf9f88ce19e230e1a4b822dca836c28cea3486b4615c37e185a6058", "generation_seconds_batch": 13.195416530943476, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1069695949554443, "target_z": 2.3437500898469428, "ce": 5.514282703399658, "genuineness": 3.6789097785949707, "identity": 0.7896463871002197, "hypothesis": "Las llaves están en la mesa de la cocina. Mire en el cajón y luego junto a la ventana. Llévatelas cuando te vayas.", "wer": 0.043478260869565216, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/22fe3709574023e51ba17aeed10ad15dcfc7c62bf31ef35ebeea75aa427056b9.mp3" }, { "id": "emo_Impatience_and_Irritability-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-1", "key": "230f92e81e7f9261b209f7b4d488edbc40ed47eae33237c021b1821832d1fb4d", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] He encontrado la cajita.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "2e058ca5b993bfa540a568cc19e2a9888370389897945b8c5bd16897f6557619", "generation_seconds_batch": 18.126249374938197, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.012240409851074219, "target_z": -0.7539062401304495, "ce": 6.181467056274414, "genuineness": 4.482243061065674, "identity": 0.5430432558059692, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/230f92e81e7f9261b209f7b4d488edbc40ed47eae33237c021b1821832d1fb4d.mp3" }, { "id": "emo_Impatience_and_Irritability-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-0", "key": "233315ba558cb29648dc10d726472c226d463af296c2c779b9ea9f2fb0ad447a", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The door is still open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "78b48c15ded369cf7437a0246c62d18ac9253a2e2344c81028d30780b4abe7c5", "generation_seconds_batch": 17.941049939021468, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3739207983016968, "target_z": -0.18945311461995548, "ce": 6.038498878479004, "genuineness": 3.7793264389038086, "identity": 0.5767778158187866, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/233315ba558cb29648dc10d726472c226d463af296c2c779b9ea9f2fb0ad447a.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-1", "key": "24528541cd63d437397acfaeca2a21e04d901857392b80e21fb75f3a9a0ebfd2", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "0bf7782c865b61099ea21a64b506a6e37e8c0482a11826976d6ecc33a8c570d7", "generation_seconds_batch": 18.919772066990845, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08129343390464783, "target_z": -0.6171875088485625, "ce": 6.252951145172119, "genuineness": 4.7332844734191895, "identity": 0.7985601425170898, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la Jette Rizanarl. Nous pouvons regarder ensemble what it contient.", "wer": 0.21052631578947367, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/24528541cd63d437397acfaeca2a21e04d901857392b80e21fb75f3a9a0ebfd2.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": "2461502f1bc2638edc528f919c45809f46f43ca30043945b034b011bab6e3a8d", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fd0dc18e42148f56f2c13768246132b4d53961a91764a860a9a87fb02ccfc65e", "generation_seconds_batch": 18.53845496091526, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0214529037475586, "target_z": 2.218750057175327, "ce": 5.486483573913574, "genuineness": 3.7040140628814697, "identity": 0.4916320741176605, "hypothesis": "La route tourne à gauche à Brinpont. Continue jusqu'à la petite barrière en bois. Je t'attendrai de l'autre côté.", "wer": 0.15, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/2461502f1bc2638edc528f919c45809f46f43ca30043945b034b011bab6e3a8d.mp3" }, { "id": "emo_Impatience_and_Irritability-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-1", "key": "24753db720eeabe6914fb4497cd370601c7076dc8beb057eaeddf6418f94d792", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] He encontrado la cajita.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "b41b1978049d84776d06c50da5149178f57c4d42f4cd2dced297c059885ce956", "generation_seconds_batch": 18.34630965802353, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4549049139022827, "target_z": 1.3906249714123364, "ce": 4.958295822143555, "genuineness": 3.6067352294921875, "identity": 0.66678786277771, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/24753db720eeabe6914fb4497cd370601c7076dc8beb057eaeddf6418f94d792.mp3" }, { "id": "emo_Impatience_and_Irritability-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-1", "key": "2475e85bc0d691e586f25d979a668815f66b4abcbd1a0b27afbd41efab7f7d05", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "9ffa0fbf32daeaaab4443c5429b5ef140c3a0dd314101add8c423e4fa31d2c72", "generation_seconds_batch": 19.673759720055386, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06258666515350342, "target_z": -0.6445312551049399, "ce": 6.38003396987915, "genuineness": 4.469690799713135, "identity": 0.5825345516204834, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/2475e85bc0d691e586f25d979a668815f66b4abcbd1a0b27afbd41efab7f7d05.mp3" }, { "id": "emo_Impatience_and_Irritability-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-0", "key": "248a2ffc60b7f5eb6691483f0817e88c6013a93053884fdd9d79d8f2afe224e8", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Tür ist noch offen.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "1733e7be79826a12b917fa3d0c59fee8a99e4b8908b8d04991653081bea6ee0b", "generation_seconds_batch": 17.869783257017843, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1283485889434814, "target_z": 2.3749998366419227, "ce": 5.720792293548584, "genuineness": 4.344170093536377, "identity": 0.38397568464279175, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/248a2ffc60b7f5eb6691483f0817e88c6013a93053884fdd9d79d8f2afe224e8.mp3" }, { "id": "emo_Impatience_and_Irritability-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-0", "key": "255ae1add79db64c87d7b41abab3f2f092809b1c895682d3cfed2911345340bd", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La puerta sigue abierta.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "c7e199e5837f2272080fb1ed44b1560983cb762e4cd002462d772c872241fd89", "generation_seconds_batch": 18.915850221994333, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15344813466072083, "target_z": -0.5117187421724254, "ce": 5.708878040313721, "genuineness": 4.268857479095459, "identity": 0.6628888845443726, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/255ae1add79db64c87d7b41abab3f2f092809b1c895682d3cfed2911345340bd.mp3" }, { "id": "emo_Impatience_and_Irritability-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-1", "key": "258ba8ff237bfb54732b1eb3867ba1ea6e9c6320ad2105ad856d1ac218a7820e", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I found the little box.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "8722876aab5bcefdd687dc097886c25b8878751d69f315221446e1f02a2a0dc1", "generation_seconds_batch": 17.969674261054024, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.01758521795272827, "target_z": -0.7617187639535025, "ce": 6.109982967376709, "genuineness": 4.005263805389404, "identity": 0.4405713677406311, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/258ba8ff237bfb54732b1eb3867ba1ea6e9c6320ad2105ad856d1ac218a7820e.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-1", "key": "25d5779e0af435d63cc7e47f0805c7f1f458f7fe4a5ed93eb9cd7448380b1718", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "7d957cf0902f24cde834b0985674db6cb9e0d2f9b3c29495bead0aed15496ba0", "generation_seconds_batch": 13.193839124054648, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4674546420574188, "target_z": -0.05273438333806854, "ce": 6.213237762451172, "genuineness": 4.168440818786621, "identity": 0.47288385033607483, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/25d5779e0af435d63cc7e47f0805c7f1f458f7fe4a5ed93eb9cd7448380b1718.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-0", "key": "2642108ca96495967eadb71b84ce64e181c2c1deac8a31c9cc32e2d2a0f29789", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La porte est encore ouverte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "c004d3e60a613411eb8234fb8e499ce97b49900e4fe3488f85e3b1904f0d2454", "generation_seconds_batch": 20.736241686041467, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22025802731513977, "target_z": -0.41406249931934136, "ce": 5.982900142669678, "genuineness": 4.432034492492676, "identity": 0.600259006023407, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/2642108ca96495967eadb71b84ce64e181c2c1deac8a31c9cc32e2d2a0f29789.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-0", "key": "26b8c2763c04d22fb8941fa5b4126e8be92a169162d66ffb51764cf9c5eae6af", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De deur staat nog open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "920dd713192345f0cbe820dc408c2d9474caa1ff961224cba3086107cac8ff08", "generation_seconds_batch": 13.282106876024045, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6612033843994141, "target_z": 0.23046879934775258, "ce": 6.046441555023193, "genuineness": 4.042920112609863, "identity": 0.38994136452674866, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/26b8c2763c04d22fb8941fa5b4126e8be92a169162d66ffb51764cf9c5eae6af.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_Impatience_and_Irritability", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": "933cf57ac5001e8e91ae691aca644cf6a0767f73601a8915689a96b1cfcc3593", "generation_seconds_batch": 14.892576234065928, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10267260670661926, "target_z": -0.5859375006806586, "ce": 6.252951145172119, "genuineness": 4.20609712600708, "identity": 0.24119684100151062, "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_Impatience_and_Irritability/26d12995a5b024b42cbe037fdee48ffb67b79df656c09f059592185aa881aca9.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-0", "key": "2785ef63f2041e74112e0aaefc71b69ea0dde46fe3a28855b1e333637614debe", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La porte est encore ouverte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "55d3e625b6104bcf4220c7a69e3b28f6816a4dc4b2f24cd22839c6c4b2c180c9", "generation_seconds_batch": 19.052202227991074, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5938694477081299, "target_z": 1.5937498938172496, "ce": 5.816103935241699, "genuineness": 4.111956596374512, "identity": 0.6732723116874695, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt ?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/2785ef63f2041e74112e0aaefc71b69ea0dde46fe3a28855b1e333637614debe.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-1", "key": "27c25e30ed5a45f6f7d2aea3d7bde7efbf8d99086a14cf227133f557ba984573", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "66cebd5fc73bbc0595a7d5b859bbef937451358c3fa9b24a6fb7b215c8928b8d", "generation_seconds_batch": 18.078579189954326, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0273215770721436, "target_z": 0.7656249823028749, "ce": 5.77639102935791, "genuineness": 3.8169827461242676, "identity": 0.3616921901702881, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/27c25e30ed5a45f6f7d2aea3d7bde7efbf8d99086a14cf227133f557ba984573.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": "27cb5813c34ec0660abf9fd42971acd07e0626dcb1e9f4d56df71e3bb513bda2", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The keys are on the kitchen table.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "04c3d0fdde60a7d69ef827a87ae3ca082693f68952aa0cbd5f425f3e2888a68f", "generation_seconds_batch": 15.842690689023584, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5142215490341187, "target_z": 0.015624960521797935, "ce": 5.816103935241699, "genuineness": 3.3368656635284424, "identity": 0.404076486825943, "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_Impatience_and_Irritability/27cb5813c34ec0660abf9fd42971acd07e0626dcb1e9f4d56df71e3bb513bda2.mp3" }, { "id": "emo_Impatience_and_Irritability-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-0", "key": "27d7ff2718fdb7bd02de66fd74949c5c10dc3894e5ed76a51222fad752ae18e2", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The door is still open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "b5b9b2ddb729dc8f6587147a16d8a4b56cad3ca9a5d9a0a22f4c6cb9c1fd9990", "generation_seconds_batch": 13.323381691006944, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19754266738891602, "target_z": -0.4472656166619315, "ce": 6.117925643920898, "genuineness": 3.8044304847717285, "identity": 0.2765541076660156, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/27d7ff2718fdb7bd02de66fd74949c5c10dc3894e5ed76a51222fad752ae18e2.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-0", "key": "2821455b1775f60ed9d3e5db3d401cd54d648148c79016d3e0331f993cb674eb", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La porte est encore ouverte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "8e41b311f7333b9d89e59bf769903d72b465ed597954580fe16442eea6a89e13", "generation_seconds_batch": 14.229802518966608, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.25633537769317627, "target_z": -0.3613281159812728, "ce": 6.24500846862793, "genuineness": 4.482243061065674, "identity": 0.6821008920669556, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/2821455b1775f60ed9d3e5db3d401cd54d648148c79016d3e0331f993cb674eb.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-1", "key": "28ebf232a48010a36c1a398d51a97fd33a8e1de68388e2cc9ab6c352440a8188", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "072d32ae42c27ae53b9ccb348786a0bd0830bd5640598e8f52197d5d95e7476e", "generation_seconds_batch": 18.262310496065766, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.049224674701690674, "target_z": -0.6640625211004183, "ce": 6.062326908111572, "genuineness": 4.168440818786621, "identity": 0.7719171643257141, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/28ebf232a48010a36c1a398d51a97fd33a8e1de68388e2cc9ab6c352440a8188.mp3" }, { "id": "emo_Impatience_and_Irritability-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-1", "key": "28eedf58fa39b1f770891eb8d22accae24689f1415cedd6890e5de5012b44521", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] He encontrado la cajita.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "76c24f660d00c83d09ea573da3664563e31b37c7b4708868bc877427a0b64fd5", "generation_seconds_batch": 19.064070543041453, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21624943614006042, "target_z": -0.41992187040555407, "ce": 5.609594821929932, "genuineness": 4.432034492492676, "identity": 0.5978010892868042, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/28eedf58fa39b1f770891eb8d22accae24689f1415cedd6890e5de5012b44521.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-1", "key": "28fd1a51fec4d7b4bbb94935a3c9467f0b79bb305386f294da398f9e206a7bb0", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "2352966bdaabaf45d9105b84ce4f1160020d6c1664dba277b119501dcb06f612", "generation_seconds_batch": 15.25431748200208, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3244814872741699, "target_z": -0.26171872039134847, "ce": 6.213237762451172, "genuineness": 4.080576419830322, "identity": 0.7003750801086426, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/28fd1a51fec4d7b4bbb94935a3c9467f0b79bb305386f294da398f9e206a7bb0.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": "291cf5028321426e3c3afb6899ea3a2ebf9acb7d943f5ae64b0e4e386966c570", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "68f77d53aac8d51760c92b765ceb0047e865e534d20394230735ef4f315d49f3", "generation_seconds_batch": 19.486686244956218, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8017923831939697, "target_z": 3.3593748761201248, "ce": 6.054384231567383, "genuineness": 3.5094566345214844, "identity": 0.575219452381134, "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_Impatience_and_Irritability/291cf5028321426e3c3afb6899ea3a2ebf9acb7d943f5ae64b0e4e386966c570.mp3" }, { "id": "emo_Impatience_and_Irritability-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-0", "key": "29515ccd6b06bbde14de7146c4f3c90ab0439c8adc1bf6cd9fa5aa3715ac05cd", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Tür ist noch offen.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "a275eb695f6c6f75e027b9221e5b40daac3362fb2b574751d106bb752f125243", "generation_seconds_batch": 14.02990688092541, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8536158800125122, "target_z": 0.5117187857345794, "ce": 6.221180438995361, "genuineness": 4.557555198669434, "identity": 0.4864547848701477, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/29515ccd6b06bbde14de7146c4f3c90ab0439c8adc1bf6cd9fa5aa3715ac05cd.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": "29b502fbcce85200008963c20355837920bde96e32e00c47352a81a247f816df", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c843ffec181b187572f9925a809170252de89f6cf2ddeadfef561adc826f7c73", "generation_seconds_batch": 16.803322314983234, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0000736713409424, "target_z": 2.1874999618831152, "ce": 5.839932441711426, "genuineness": 3.936227321624756, "identity": 0.5339597463607788, "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_Impatience_and_Irritability/29b502fbcce85200008963c20355837920bde96e32e00c47352a81a247f816df.mp3" }, { "id": "emo_Impatience_and_Irritability-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-1", "key": "2a10fe6a982688215940444908c447425b621e1698ca07ef326df717cdb527a3", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I found the little box.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "e4272956e129faa0efd1f6fda5dce5f1883f497776d38d09d6802ea6d2886592", "generation_seconds_batch": 18.841351971961558, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0469815731048584, "target_z": -0.8046875142938318, "ce": 6.197352409362793, "genuineness": 4.20609712600708, "identity": 0.5284022092819214, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/2a10fe6a982688215940444908c447425b621e1698ca07ef326df717cdb527a3.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": "2a64f5ab2b22936942b93800ba0c2df0fa79f57bbc377abaff14bff0deb22fbf", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7af15a15e1194f0981481f625e4702cd54fc4a498d2d105c9ad209aeef40c22c", "generation_seconds_batch": 13.313538247020915, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.064211130142212, "target_z": 2.281249899262519, "ce": 5.839932441711426, "genuineness": 4.030367851257324, "identity": 0.24774357676506042, "hypothesis": "Iemand heeft het kleine blauwe stoeltje verplaatst. Dat stond hier naast de hoge boekenkast. We zetten het na de lunch terug.", "wer": 0.047619047619047616, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/2a64f5ab2b22936942b93800ba0c2df0fa79f57bbc377abaff14bff0deb22fbf.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-1", "key": "2ae3797b5b7b832284f4258afacc6a15671b5b634ce60be5b703c9e09fdb82b4", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "9d2fd07c8ca9d196c5c948e1b84d0daff9caf4566dbdcbf55eeb390ac330304f", "generation_seconds_batch": 17.705651398049667, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5315921306610107, "target_z": 0.041015597603489086, "ce": 6.0305562019348145, "genuineness": 4.2374773025512695, "identity": 0.5351046323776245, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/2ae3797b5b7b832284f4258afacc6a15671b5b634ce60be5b703c9e09fdb82b4.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-1", "key": "2aec4baf1142449975e51d07f2bd81a005786aa7864ce7cbfaccc52da99a0ba3", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "3064fe161470eb36b7aabbc9aae38f32cb6054dc9de90cb14ac5e4a36a1f7c74", "generation_seconds_batch": 20.489676662022248, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0251731276512146, "target_z": -0.6992187476176948, "ce": 6.348263263702393, "genuineness": 4.557555198669434, "identity": 0.6288668513298035, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/2aec4baf1142449975e51d07f2bd81a005786aa7864ce7cbfaccc52da99a0ba3.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-0", "key": "2b580ed20c7227a8c01f0960acd52b8e50d15fd02e9a9eee68d691383e136b64", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De deur staat nog open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "3297dacf05eac3d47bd4c587e9dc4385c3776098e52076a911b82a4095fea99f", "generation_seconds_batch": 13.259298200020567, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0059423446655273, "target_z": 0.734374887010663, "ce": 6.117925643920898, "genuineness": 4.2249250411987305, "identity": 0.6038864850997925, "hypothesis": "De deur staat nog open. Ik heb je jaas 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_Impatience_and_Irritability/2b580ed20c7227a8c01f0960acd52b8e50d15fd02e9a9eee68d691383e136b64.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-1", "key": "2bd03e616d7821aab358f99a50880b8951eb16a7428138a6732a222044e52623", "bucket": "emo_Impatience_and_Irritability", "phase": "wording", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "91518918f0fa50cc52f0130b7cb9060209abc2452097789c2eab5b13971fda73", "generation_seconds_batch": 14.222604966023937, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3659036159515381, "target_z": -0.20117185679238095, "ce": 6.125868320465088, "genuineness": 4.394378662109375, "identity": 0.5492873191833496, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/2bd03e616d7821aab358f99a50880b8951eb16a7428138a6732a222044e52623.mp3" }, { "id": "emo_Impatience_and_Irritability-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-0", "key": "2c7c5ea4ee782a460ad0241d4464522318935ae70c8cc150155b02919afc3720", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Tür ist noch offen.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "f9ed8cd85bcc6998be17c2dba817f3ef2ba38d8dcd0fe9417ea6a17396fcb910", "generation_seconds_batch": 18.216588776092976, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.615248680114746, "target_z": 1.6249999891094615, "ce": 6.213237762451172, "genuineness": 4.250029563903809, "identity": 0.41520413756370544, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/2c7c5ea4ee782a460ad0241d4464522318935ae70c8cc150155b02919afc3720.mp3" }, { "id": "emo_Impatience_and_Irritability-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-0", "key": "2cdc1d1b7381bdb7f4d1ce49c1b465b053731117745e1833ac8ff6262dd29099", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The door is still open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "ea3125730ea4957c22ffaa5f9623314e7540d43a21bef0df43e1718d839ee33a", "generation_seconds_batch": 13.233545263065025, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1320689618587494, "target_z": -0.5429687503403293, "ce": 6.173524379730225, "genuineness": 3.9425034523010254, "identity": 0.3021273910999298, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/2cdc1d1b7381bdb7f4d1ce49c1b465b053731117745e1833ac8ff6262dd29099.mp3" }, { "id": "emo_Impatience_and_Irritability-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-0", "key": "2cdeb9fcb71ab72abefc5bf299cd5d25c2fc2f8b75342bedf70c9378069201e4", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La puerta sigue abierta.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "ee5dc8873842c2f4fd704dea85b191b057651491e6e8d20416233499f8bb00ba", "generation_seconds_batch": 19.853847934980877, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18017208576202393, "target_z": -0.47265625374362263, "ce": 5.764476776123047, "genuineness": 4.287685871124268, "identity": 0.55306077003479, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/2cdeb9fcb71ab72abefc5bf299cd5d25c2fc2f8b75342bedf70c9378069201e4.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-0", "key": "2cf56858ae5434d2b6f1c3ea59a591d03b4a2b088a9c2e05cf188a891dbf226c", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La porte est encore ouverte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "da7e715b186433c39148b2d901120c61ac2474d9db76ead001aefb04739765b6", "generation_seconds_batch": 18.14116199896671, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22025802731513977, "target_z": -0.41406249931934136, "ce": 6.205295085906982, "genuineness": 4.833701133728027, "identity": 0.6393178701400757, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/2cf56858ae5434d2b6f1c3ea59a591d03b4a2b088a9c2e05cf188a891dbf226c.mp3" }, { "id": "emo_Impatience_and_Irritability-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-1", "key": "2d37f5ece186049519dbd4dc898f3b1eb9133588dac58092c908f2b7464311b9", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I found the little box.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "820d91f662ba24ca413157419820bda59d3bcb943158a69b4a4b87d517cdaf7c", "generation_seconds_batch": 14.606093233102001, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.46077364683151245, "target_z": -0.06250001633580775, "ce": 5.7684478759765625, "genuineness": 3.6914620399475098, "identity": 0.5425933003425598, "hypothesis": "I found the little box. It was beside the old Wingan. Look inside together.", "wer": 0.1875, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/2d37f5ece186049519dbd4dc898f3b1eb9133588dac58092c908f2b7464311b9.mp3" }, { "id": "emo_Impatience_and_Irritability-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-1", "key": "2de10cef3f70fd1c52bd540c9ee93fd3ffda23647671de3bc1a2045340dae98b", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] He encontrado la cajita.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "41b88388baebf62f81602ce8f057c70fdeceac416ee6f6eb8d9b46cbfcef905d", "generation_seconds_batch": 18.15506736910902, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11068978905677795, "target_z": -0.5742187585082332, "ce": 6.149696350097656, "genuineness": 4.607763767242432, "identity": 0.6326917409896851, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/2de10cef3f70fd1c52bd540c9ee93fd3ffda23647671de3bc1a2045340dae98b.mp3" }, { "id": "emo_Impatience_and_Irritability-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-0", "key": "2de98b355e0b39ad08b542b823417d6e1e23862a88e3ece516d69687525de7c5", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The door is still open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "006c391752721484f20cb04fc96ce6ce2dadc14d9a4c95d562cf3b088cab8e1b", "generation_seconds_batch": 18.799302662024274, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4442152976989746, "target_z": 1.3749999237662305, "ce": 5.764476776123047, "genuineness": 3.4843525886535645, "identity": 0.2889713644981384, "hypothesis": "The 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_Impatience_and_Irritability/2de98b355e0b39ad08b542b823417d6e1e23862a88e3ece516d69687525de7c5.mp3" }, { "id": "emo_Impatience_and_Irritability-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-1", "key": "2df4720e8097a47362a6cb9732ceb6cf1503230aa2ba8783ad38ed8a80ffcaae", "bucket": "emo_Impatience_and_Irritability", "phase": "wording", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I found the little box.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "ea3b9e343661b9fafd2b86a210ec7939bfe59ec5f0f7ef94678f461e8a46b0a5", "generation_seconds_batch": 15.369086752063595, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.025602400302886963, "target_z": -0.7734375061259279, "ce": 6.2767791748046875, "genuineness": 4.419482707977295, "identity": 0.5365591049194336, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/2df4720e8097a47362a6cb9732ceb6cf1503230aa2ba8783ad38ed8a80ffcaae.mp3" }, { "id": "emo_Impatience_and_Irritability-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-0", "key": "2eda86159a2e73f3f1f031dc8901349efd523502de34087050aabce2397e4238", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The door is still open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "7b6a3939b35f264028a6fecd2dbf30eedf0c92b6ca95016713a632a5f8c9f19b", "generation_seconds_batch": 19.159221982001327, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14543095231056213, "target_z": -0.5234374843448509, "ce": 6.078212261199951, "genuineness": 3.9550557136535645, "identity": 0.292201966047287, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/2eda86159a2e73f3f1f031dc8901349efd523502de34087050aabce2397e4238.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-1", "key": "2ef3131d47a6600a0cd3c75aa3839de81711dae0a0ebc68f3d08639609410f3c", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "65e6fa91cd2afbdf2a242318a091b364dbf42a90a68aeb9fba6ede5935f98009", "generation_seconds_batch": 19.250044613028876, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1759278774261475, "target_z": 3.9062499754962885, "ce": 5.689021587371826, "genuineness": 3.3996260166168213, "identity": 0.5156485438346863, "hypothesis": "Ik heb een kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/2ef3131d47a6600a0cd3c75aa3839de81711dae0a0ebc68f3d08639609410f3c.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": "2f2bd5a8ad7bd22b697c0d5467759bea3be07ad3ad07634c4637e9066b2cbdf2", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "56186aae15091e587c8f5d2269a763b979a96519b248c8675e72cd4490da8b43", "generation_seconds_batch": 15.05838883400429, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15344813466072083, "target_z": -0.5117187421724254, "ce": 5.708878040313721, "genuineness": 4.18726921081543, "identity": 0.7179259061813354, "hypothesis": "J'ai écrit le numéro sur l'enveloppe. Lise bien et verifie les deux derniers chiffres. Appelle-moi quand you're a moment.", "wer": 0.2727272727272727, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/2f2bd5a8ad7bd22b697c0d5467759bea3be07ad3ad07634c4637e9066b2cbdf2.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-0", "key": "2fb858d80f80517a7f9ef0db131234f0cbc634d9050a891cd8f7f505d1456d92", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De deur staat nog open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "6e5cc7039d592d83b618162c291a86584736d886a77ca0d8cfc49d415f23b9ff", "generation_seconds_batch": 12.991865167976357, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4816288948059082, "target_z": 1.4296875034032932, "ce": 5.959072113037109, "genuineness": 4.13078498840332, "identity": 0.47928595542907715, "hypothesis": "De deur 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_Impatience_and_Irritability/2fb858d80f80517a7f9ef0db131234f0cbc634d9050a891cd8f7f505d1456d92.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": "30bcc14e38f07d0addc4eabc97b0a2af6737ffe46a39a7dc2713ae75f3edbf3d", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e2bec3cbca1ba03b1213a6de7c663d777bab6cb286d90df95a8156aa13579e5d", "generation_seconds_batch": 18.37734621495474, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.496615409851074, "target_z": 4.375000010890538, "ce": 5.254160404205322, "genuineness": 3.3713839054107666, "identity": 0.6102254390716553, "hypothesis": "Las llaves están en la mesa de la cocina. Miré en el cajón y luego la ventana. Llévatelos cuando te vayas.", "wer": 0.13043478260869565, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/30bcc14e38f07d0addc4eabc97b0a2af6737ffe46a39a7dc2713ae75f3edbf3d.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-0", "key": "30e30e51244eadcf2fe4d116f33672915f3ea46fddb8e09e685a600a8090c04a", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De deur staat nog open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "010172aaebf472fd487ab959b15c5476b6575376825cb2b8ae0d21b2546119d3", "generation_seconds_batch": 18.445135482004844, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3244814872741699, "target_z": -0.26171872039134847, "ce": 6.165581703186035, "genuineness": 4.419482707977295, "identity": 0.31919804215431213, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/30e30e51244eadcf2fe4d116f33672915f3ea46fddb8e09e685a600a8090c04a.mp3" }, { "id": "emo_Impatience_and_Irritability-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-1", "key": "314445579db5cf58e34c43dcb09a3bd2786ebaeeee2631aea9ed001a8f8e8935", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I found the little box.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "add6e5b3d27bab123b51ca78079bf2dde3079ca40b884537007e599a4970dc0a", "generation_seconds_batch": 18.974736292962916, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.08439511060714722, "target_z": -0.8593750068065865, "ce": 6.372091293334961, "genuineness": 4.15588903427124, "identity": 0.5203150510787964, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/314445579db5cf58e34c43dcb09a3bd2786ebaeeee2631aea9ed001a8f8e8935.mp3" }, { "id": "emo_Impatience_and_Irritability-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-1", "key": "3173515ef2f6e1809f695f92d599121f1683e5a570cac2cdb73627b77c67cbb7", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] He encontrado la cajita.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "ddeb31eca9d1b125df8f73e3369170da5c67cb559c9eb8ba6f5e3746dd45e0fe", "generation_seconds_batch": 18.864614384016022, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12939655780792236, "target_z": -0.5468750122518559, "ce": 5.831989288330078, "genuineness": 4.507347106933594, "identity": 0.7155660390853882, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/3173515ef2f6e1809f695f92d599121f1683e5a570cac2cdb73627b77c67cbb7.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": "3181e5a3671a7af38fd13a087a70b7dc79ef1407145dddd330219f58ea03378a", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f7e38991387368c5674c31ae3a1bf0091427f89aa5bffc8d495cb5e8601f39fa", "generation_seconds_batch": 20.05405311100185, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9252467155456543, "target_z": 2.0781251511062218, "ce": 5.613565921783447, "genuineness": 3.835810661315918, "identity": 0.4423091411590576, "hypothesis": "J'ai écrit le numéro sur l'enveloppe. Lis-le bien et verifie les deux derniers chiffres. Appelle-moi quand tu auras un moment.", "wer": 0.045454545454545456, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/3181e5a3671a7af38fd13a087a70b7dc79ef1407145dddd330219f58ea03378a.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-0", "key": "319927615d45fa23b61cd0603ff8eb549ef6ce87dfac92146550566f745e3903", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La porte est encore ouverte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "964d89e6479c0ab9a3c30889e839ce0d278624980d35890afb962bbe1c6953ac", "generation_seconds_batch": 19.242655509035103, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0807695388793945, "target_z": 0.8437500462847887, "ce": 6.133810997009277, "genuineness": 4.3127899169921875, "identity": 0.5159527659416199, "hypothesis": "La porte est encore ouverte J'ai posé ton manteau sur la chaise Dis-moi quand tu es prêt", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/319927615d45fa23b61cd0603ff8eb549ef6ce87dfac92146550566f745e3903.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": "321faeb89cc3adecb0defe3cf86fc83022c4de255bf1fb3cc7bb794444086126", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b057501ff3cb112e7dd20b93bd2a3a2a5ee4b4634d5abb8e696275832c802851", "generation_seconds_batch": 13.17327401903458, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.368340253829956, "target_z": 4.187499787634499, "ce": 5.696964263916016, "genuineness": 3.8044304847717285, "identity": 0.3104272484779358, "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_Impatience_and_Irritability/321faeb89cc3adecb0defe3cf86fc83022c4de255bf1fb3cc7bb794444086126.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": "325f63e4745f656f75e2b04bd66cc218a56707890e6d97b50fde5c230d8f5402", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "53d5b9a0190cfdc3f78f0c71507d4fb00ae0e755fdf887b3b5df9779c398b358", "generation_seconds_batch": 13.601456040982157, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0487008094787598, "target_z": 0.7968750775950868, "ce": 5.982900142669678, "genuineness": 3.7918784618377686, "identity": 0.4521246552467346, "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_Impatience_and_Irritability/325f63e4745f656f75e2b04bd66cc218a56707890e6d97b50fde5c230d8f5402.mp3" }, { "id": "emo_Impatience_and_Irritability-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-0", "key": "32e3a387c06d0ea01980591301a5306fa624082a556f652e0fac9467ba30471b", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Tür ist noch offen.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "27af4627b55f9396f0f972a9f225918d707f845dcaa13a43afb919aa1b81804e", "generation_seconds_batch": 17.59608573501464, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3052507638931274, "target_z": 1.1718750013613173, "ce": 6.038498878479004, "genuineness": 4.319066047668457, "identity": 0.7018191814422607, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/32e3a387c06d0ea01980591301a5306fa624082a556f652e0fac9467ba30471b.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-1", "key": "32e910945eda234420edf1a29a3e5c35923e1adf6a28110df052becf2f703303", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "9f80f1da20e7052145e28ad64f2a0a8157066b6e67574b8f337313d24ccbec63", "generation_seconds_batch": 17.861022870987654, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8343851566314697, "target_z": 1.9453125074872453, "ce": 6.006728172302246, "genuineness": 3.7667744159698486, "identity": 0.26974791288375854, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/32e910945eda234420edf1a29a3e5c35923e1adf6a28110df052becf2f703303.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": "32fb3c80994d741a64f6932fce6757be538f086b687d0343ac3aa998723bf7fe", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "c6763f8ca2b970d82f7b18115b2af63b286e16ee2f007d8a6c7a4917bd36f2c0", "generation_seconds_batch": 18.53845496091526, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.55593204498291, "target_z": 3.0, "ce": 5.919358730316162, "genuineness": 3.9550557136535645, "identity": 0.6329132318496704, "hypothesis": "La retourne à gauche après le pont continue jusqu'à la petite barrière en bois. Je t'attendrai de l'autre côté.", "wer": 0.1, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/32fb3c80994d741a64f6932fce6757be538f086b687d0343ac3aa998723bf7fe.mp3" }, { "id": "emo_Impatience_and_Irritability-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-0", "key": "33d8ccdabbc82f52dba5355595f609c688d7bbbd99e3f46fe84433f436a7722e", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The door is still open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "d55fc69bb25310800f6f3d0fbed4f1e163ab74be42b20dd608bb081dddba6be0", "generation_seconds_batch": 19.159221982001327, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12939655780792236, "target_z": -0.5468750122518559, "ce": 6.125868320465088, "genuineness": 3.9927117824554443, "identity": 0.47560226917266846, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/33d8ccdabbc82f52dba5355595f609c688d7bbbd99e3f46fe84433f436a7722e.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_Impatience_and_Irritability", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": "1a045f442e0d0148c31f412809e70dbc3c30527411456331d6f8110f7f668a57", "generation_seconds_batch": 13.2070917369565, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19353407621383667, "target_z": -0.4531249877481442, "ce": 6.149696350097656, "genuineness": 4.344170093536377, "identity": 0.7203371524810791, "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_Impatience_and_Irritability/33f63538ac2c49676cc53462aa2024b47e58cb29b8690774a6580785ecb0e60e.mp3" }, { "id": "emo_Impatience_and_Irritability-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-1", "key": "33f7a99ce7a24cdcf4d9225075f21a35112d80843d5487a0e29018bc37cc1a4b", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] He encontrado la cajita.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "eb99770b57d43284fa648e91db9afc99bfca3830960c6e143e3881d7270e258d", "generation_seconds_batch": 18.864614384016022, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.038535118103027344, "target_z": -0.6796874816222163, "ce": 5.959072113037109, "genuineness": 4.632867813110352, "identity": 0.5964409112930298, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/33f7a99ce7a24cdcf4d9225075f21a35112d80843d5487a0e29018bc37cc1a4b.mp3" }, { "id": "emo_Impatience_and_Irritability-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-0", "key": "341f8c7b1fd7ebfdb14800b92fa5745f90a855c9dac3ec13db020eed246d2859", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La puerta sigue abierta.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "92497f78a94b0835f6cc5fa493ca5f2d3a84d2acefee308b5fdaaa90ac0565eb", "generation_seconds_batch": 18.041341340984218, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.194870263338089, "target_z": -0.4511718785734579, "ce": 5.935244083404541, "genuineness": 4.319066047668457, "identity": 0.49283939599990845, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/341f8c7b1fd7ebfdb14800b92fa5745f90a855c9dac3ec13db020eed246d2859.mp3" }, { "id": "emo_Impatience_and_Irritability-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-1", "key": "3454396c7a428e5191dc8e47dd78f970245de29f5f5e913c3c6a3a7ee8a30616", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "8e7c1253472e7fffcfc5bc381844dd79cdd56ede7913639b94b9eb1ab7e98717", "generation_seconds_batch": 18.35392912500538, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0786210298538208, "target_z": -0.621093770760089, "ce": 6.324435234069824, "genuineness": 4.632867813110352, "identity": 0.6530987024307251, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/3454396c7a428e5191dc8e47dd78f970245de29f5f5e913c3c6a3a7ee8a30616.mp3" }, { "id": "emo_Impatience_and_Irritability-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-0", "key": "347ab44bd1360724ea0769c765267878e2ce759a32a19d903684390930708de7", "bucket": "emo_Impatience_and_Irritability", "phase": "wording", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The door is still open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "5754239946e1c441678e91c3d8efaae5e30bd52714b0d6c65c9a28d7f8c8d26b", "generation_seconds_batch": 14.085063438047655, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08396583795547485, "target_z": -0.613281246937036, "ce": 6.252951145172119, "genuineness": 4.337893962860107, "identity": 0.28505629301071167, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/347ab44bd1360724ea0769c765267878e2ce759a32a19d903684390930708de7.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_Impatience_and_Irritability", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": "8a90d28ef4392449d6e0f39a08df76520481b6a13dfd22959e9d521d82bbaece", "generation_seconds_batch": 14.830674357013777, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09465542435646057, "target_z": -0.5976562428530842, "ce": 6.41180419921875, "genuineness": 4.306513786315918, "identity": 0.41110455989837646, "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_Impatience_and_Irritability/347b084eb1c87968a3fc14b855043a2de140e81cf0874b7d65525285bfb31414.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": "3617618d785ef24170e011e6a18a4531bb33bdd49d9a98dc11f005be4a5e948d", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "1bca054143cee1861d27f2e162459d69dec64e3a654df5a208eb49c7658dc6c7", "generation_seconds_batch": 21.12665927200578, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3635194301605225, "target_z": 2.7187498393645573, "ce": 5.4666266441345215, "genuineness": 3.452972412109375, "identity": 0.4710337221622467, "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": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/3617618d785ef24170e011e6a18a4531bb33bdd49d9a98dc11f005be4a5e948d.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-1", "key": "3693c3e9dc23dbc6fe0659e2a31a3cfc357fd9b3f5a83d19bfb20b3d2dd32f00", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "754a8b6d3b974259be452d36e90e1e27908ca46a2ef2c0f030f23d0e62651122", "generation_seconds_batch": 17.93838132591918, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5663332939147949, "target_z": 0.09179687176687139, "ce": 5.808161735534668, "genuineness": 3.973883628845215, "identity": 0.5755985975265503, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/3693c3e9dc23dbc6fe0659e2a31a3cfc357fd9b3f5a83d19bfb20b3d2dd32f00.mp3" }, { "id": "emo_Impatience_and_Irritability-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-1", "key": "36a27855fbda736957b9e4899e4812f705f0e14dc62f7e6b55ba5c2ac2883836", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] He encontrado la cajita.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "0bc75d78a1c08ccdf867b2a157fa8fdbdd0f797e828cd0f45cc9aa7b760d2764", "generation_seconds_batch": 17.9396568860393, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1507757306098938, "target_z": -0.515625004083952, "ce": 6.046441555023193, "genuineness": 4.482243061065674, "identity": 0.592695415019989, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/36a27855fbda736957b9e4899e4812f705f0e14dc62f7e6b55ba5c2ac2883836.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-0", "key": "3752b17b657b9a7077c4eeaddd76bbf9bba1d60551bd412276735fdd17536758", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La porte est encore ouverte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "924fdf53aa20225d9d04e9532d0b37da3d3cff91ba8471224b8762b4b8b6fa71", "generation_seconds_batch": 17.954309733002447, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7627543807029724, "target_z": 0.37890622923991096, "ce": 6.062326908111572, "genuineness": 4.099404335021973, "identity": 0.5311719179153442, "hypothesis": "La porte est encore ouverte. Je 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_Impatience_and_Irritability/3752b17b657b9a7077c4eeaddd76bbf9bba1d60551bd412276735fdd17536758.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-1", "key": "3757179615cf82cac3faddfc9891531c3e4fccd0919f9e955be3fc779ac553ae", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5e4328147f366a4a03ba20014492c7fcbfad1f4220931c7b7a69d1d0ea31b356", "generation_seconds_batch": 12.987187399994582, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23896479606628418, "target_z": -0.38671875306296394, "ce": 6.165581703186035, "genuineness": 4.7081804275512695, "identity": 0.7422124147415161, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/3757179615cf82cac3faddfc9891531c3e4fccd0919f9e955be3fc779ac553ae.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-1", "key": "38134ed501522599fbe956dfd3e9564f1afd21f72b1ddda92b549b0c1b685605", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "8ceab15be65f3adde0b2d48cefd1d3253acf013c0362a437134d98e2e778212b", "generation_seconds_batch": 19.029261486022733, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4581012725830078, "target_z": -0.06640623468518024, "ce": 5.685050010681152, "genuineness": 4.13078498840332, "identity": 0.5641581416130066, "hypothesis": "Je trouvais la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.10526315789473684, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/38134ed501522599fbe956dfd3e9564f1afd21f72b1ddda92b549b0c1b685605.mp3" }, { "id": "emo_Impatience_and_Irritability-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-0", "key": "386935f4391d3015da1a4079089cc0a23bc1a409b174463c7ecf41d66fcdf3ed", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The door is still open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fb76bc7ac01538dbae09d97ce68929a52236ae6d398c50f581e45b911785edc0", "generation_seconds_batch": 20.243516954011284, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.30042991042137146, "target_z": -0.2968749904707788, "ce": 6.054384231567383, "genuineness": 3.6914620399475098, "identity": 0.4249209761619568, "hypothesis": "The door still open. I c 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_Impatience_and_Irritability/386935f4391d3015da1a4079089cc0a23bc1a409b174463c7ecf41d66fcdf3ed.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": "39057fb566bcee6eb82453b85970e12caf0d55c19155896d5c21842c7a0489a8", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "703d6e68974bd499edca5e2ce4e9047a74bbcc3c6f4d152bd99fbc46ccfbfb91", "generation_seconds_batch": 14.292289865086786, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7435235977172852, "target_z": 1.8124998638682688, "ce": 5.863759994506836, "genuineness": 4.061748504638672, "identity": 0.6920865774154663, "hypothesis": "La route tourne à gauche après le pont. Continue jusqu'à la petite barrière en bois. Je t'attendrai d'autre côté.", "wer": 0.1, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/39057fb566bcee6eb82453b85970e12caf0d55c19155896d5c21842c7a0489a8.mp3" }, { "id": "emo_Impatience_and_Irritability-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-1", "key": "3997b990a3dd49f47144168bc8b9bc2d25a0a4dca1ffed7661702e9b139852ee", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "c0cb272791d5ddcf576c9462192ab5f33a0527b643185b87a79d7b43738d10f5", "generation_seconds_batch": 20.153466693940572, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.022500723600387573, "target_z": -0.7031250095292212, "ce": 6.316492557525635, "genuineness": 4.375550270080566, "identity": 0.656002402305603, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/3997b990a3dd49f47144168bc8b9bc2d25a0a4dca1ffed7661702e9b139852ee.mp3" }, { "id": "emo_Impatience_and_Irritability-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-1", "key": "399fc8c2d50a61bd88663445cc0923b62ec471d9de3b962416551e80c1c48bf1", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I found the little box.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "c64cb03fbff8cc3f483abefe602b4f5eddb163fe036f0f9a3544ba4e1537e683", "generation_seconds_batch": 17.98840181902051, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.1271534562110901, "target_z": -0.9218750231423943, "ce": 6.3641486167907715, "genuineness": 4.432034492492676, "identity": 0.2736032009124756, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/399fc8c2d50a61bd88663445cc0923b62ec471d9de3b962416551e80c1c48bf1.mp3" }, { "id": "emo_Impatience_and_Irritability-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-1", "key": "39ba36904fc2f8134507be062b1438539678e0f38fc6f25029dc314bbb71f249", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "4f415d2e74f34f6685908f4f6061689e9a0c8926ce963dd146dd8eb482cf5603", "generation_seconds_batch": 13.284366386011243, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08931061625480652, "target_z": -0.605468766676137, "ce": 6.435632705688477, "genuineness": 4.432034492492676, "identity": 0.5629047155380249, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/39ba36904fc2f8134507be062b1438539678e0f38fc6f25029dc314bbb71f249.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-0", "key": "39cdade1694af5af0e0c6c2405e703c5f6e0960590387a53f072bf74f20d838b", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De deur staat nog open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "1c7474c1fd6f21d54ee869887e8cdfeb578a1185be1e9a32eec28c8b1d0f4d7e", "generation_seconds_batch": 17.730114877107553, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3426642417907715, "target_z": 1.226562406749764, "ce": 5.597680568695068, "genuineness": 3.8295347690582275, "identity": 0.6438403725624084, "hypothesis": "De deur 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_Impatience_and_Irritability/39cdade1694af5af0e0c6c2405e703c5f6e0960590387a53f072bf74f20d838b.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-1", "key": "3acac2134a7ffe0527e99502b6b2dfe94cc6546e0dc1730deef0add1db244b22", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "984fa6acf19fa1a1c21b2a811b15f5f5c362981a6c7836a035427d4c211533f8", "generation_seconds_batch": 21.192283648997545, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.957315444946289, "target_z": 2.1250001197959234, "ce": 6.054384231567383, "genuineness": 3.503180742263794, "identity": 0.4907870590686798, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/3acac2134a7ffe0527e99502b6b2dfe94cc6546e0dc1730deef0add1db244b22.mp3" }, { "id": "emo_Impatience_and_Irritability-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-0", "key": "3b296d332ad7b0bf56f2decabcfff4742630f4cab540b2a85a546703af9c62b0", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La puerta sigue abierta.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "8ac4452b6d54e1138b6cbe66300bf1dfb77a374e74f7691f9920a2c02617ec86", "generation_seconds_batch": 21.349059412023053, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1288726329803467, "target_z": 0.9140624993193414, "ce": 5.736677646636963, "genuineness": 4.061748504638672, "identity": 0.5759450197219849, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/3b296d332ad7b0bf56f2decabcfff4742630f4cab540b2a85a546703af9c62b0.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-0", "key": "3b9d33b07dd5eea98c02f2f9ffff60119caa339ca96ba996b370acb7f3367fbf", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De deur staat nog open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "9a07f3922b54bd173e6e0c8d11693785b5c4ae21ad5fa6b5f4a1515cfe32561e", "generation_seconds_batch": 18.489454717026092, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7507286071777344, "target_z": 0.3613281159812728, "ce": 6.125868320465088, "genuineness": 4.268857479095459, "identity": 0.4360940754413605, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/3b9d33b07dd5eea98c02f2f9ffff60119caa339ca96ba996b370acb7f3367fbf.mp3" }, { "id": "emo_Impatience_and_Irritability-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-1", "key": "3b9fb8aa25d480228875e2e7af33d1c2b4405835a7d2b57cd6fe50d005e4a538", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] He encontrado la cajita.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "1eb77a573cb60894e57baf8ebb6ccb868f2c1d4228afae7aaf4fc1d9ed39f6c0", "generation_seconds_batch": 13.052403626032174, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16146531701087952, "target_z": -0.5, "ce": 6.006728172302246, "genuineness": 4.570107460021973, "identity": 0.7237188816070557, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/3b9fb8aa25d480228875e2e7af33d1c2b4405835a7d2b57cd6fe50d005e4a538.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-0", "key": "3be76dbd67d157aa6482c066fc4cc9aed51c7a36be8b06e0178dfcc9fbf216ca", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La porte est encore ouverte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "8cdbc68e3a938f540ff5ca2089498d96c036ecaa8de369a28f51776fad68730b", "generation_seconds_batch": 15.539749585906975, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7055861949920654, "target_z": 3.218749970051019, "ce": 5.959072113037109, "genuineness": 4.036643981933594, "identity": 0.1633986234664917, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/3be76dbd67d157aa6482c066fc4cc9aed51c7a36be8b06e0178dfcc9fbf216ca.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-1", "key": "3c271df8aabc5eaaeb9cca11d3f0de497f16678468db05e98b83f045ef77a859", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "14f38f699ea7327cffef4ce98e8c80e11410e3a3002d167cf55acdbe9c95a844", "generation_seconds_batch": 19.68378479394596, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6411603689193726, "target_z": 0.20117185679238095, "ce": 6.109982967376709, "genuineness": 4.406930446624756, "identity": 0.7247879505157471, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude deurraam. 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_Impatience_and_Irritability/3c271df8aabc5eaaeb9cca11d3f0de497f16678468db05e98b83f045ef77a859.mp3" }, { "id": "emo_Impatience_and_Irritability-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-0", "key": "3c2b1819eaa73c3eb75d2ab4825b8e707666c8735289a5ec7012a992285a2eea", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The door is still open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "f756d1af7040e9e51bbe0f3d2e0e8780f82aa1735db9e8d32741512f7322ddd8", "generation_seconds_batch": 17.91326364199631, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3907674551010132, "target_z": 1.296875034032933, "ce": 5.919358730316162, "genuineness": 3.7416701316833496, "identity": 0.3476249873638153, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/3c2b1819eaa73c3eb75d2ab4825b8e707666c8735289a5ec7012a992285a2eea.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_Impatience_and_Irritability", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": "b9e6ff6657e966ae0c0362558c2dc6e458ce84e1558fb1ebc0f034e4e2451122", "generation_seconds_batch": 14.637364013004117, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13741374015808105, "target_z": -0.5351562700794303, "ce": 6.173524379730225, "genuineness": 4.444586753845215, "identity": 0.7937038540840149, "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_Impatience_and_Irritability/3c590f9302048ad206a88d3c2440f1028cc9eea1f1662250baf365be21a6ebfa.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": "3c80e325dd5004c5167c12c324f635466405dcbccbfa09ac36e33588332483ce", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "228e4d4e12ca0edb1b085bf5cb958ff5a1969b5a24ba25dad4ffe3b399553904", "generation_seconds_batch": 15.429349728976376, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12939655780792236, "target_z": -0.5468750122518559, "ce": 6.0146708488464355, "genuineness": 4.469690799713135, "identity": 0.5024335384368896, "hypothesis": "Les clés sont sur la table de la cuisine. J'y regardais dans le tiroir, puis près de la fenêtre. Prends les quand tu partiras.", "wer": 0.08333333333333333, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/3c80e325dd5004c5167c12c324f635466405dcbccbfa09ac36e33588332483ce.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": "3d17798a324b70eb3501f42631786d9b68381f615bb8324e75aea8a77cd39d9b", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1f794c8ac558c16f0204400de52fe866d86f5979dd8aaea8930f9f6c07ba7ffd", "generation_seconds_batch": 13.30133551300969, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.58213210105896, "target_z": 4.500000043562154, "ce": 5.863759994506836, "genuineness": 3.6349775791168213, "identity": 0.3750053644180298, "hypothesis": "Die Schlüsse liegen auf dem Küchentisch. Ich suche in der Schublade daneben dem Fenster. Nimm sie mit, wenn du gehst.", "wer": 0.19047619047619047, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/3d17798a324b70eb3501f42631786d9b68381f615bb8324e75aea8a77cd39d9b.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": "3d4faf1c41876e7850d0b753901a0d8b40dbec8b13e54f4fe5708fe06f850160", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Someone moved the little blue chair.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1ace23fc262aa3a64a575ef174d42a16c928b5f350dc864c35d50b4fc9cb1ef4", "generation_seconds_batch": 13.28623522107955, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1689585447311401, "target_z": 0.9726562101814686, "ce": 5.95112943649292, "genuineness": 3.4686625003814697, "identity": 0.21072129905223846, "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_Impatience_and_Irritability/3d4faf1c41876e7850d0b753901a0d8b40dbec8b13e54f4fe5708fe06f850160.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-1", "key": "3da76420f49e2c25316019b8e73ebd478560c479008234812033e1e6b9e4c9ea", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "945fae710805fcb5ed8ff2aa73ac370c1f2f12127ddcadece20c3954a1a5aff6", "generation_seconds_batch": 24.223658098024316, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05991426110267639, "target_z": -0.6484375170164665, "ce": 6.0146708488464355, "genuineness": 4.595211505889893, "identity": 0.7366653084754944, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/3da76420f49e2c25316019b8e73ebd478560c479008234812033e1e6b9e4c9ea.mp3" }, { "id": "emo_Impatience_and_Irritability-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-0", "key": "3dca9a4cdb77a9e6ea3c68f97da7d062453b5c933e0727bcccf9ca41c690e71d", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La puerta sigue abierta.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "861aeba475a2dd8079e47000095a6b7d9cab52d9a16aea63ab24b99c09fe71b4", "generation_seconds_batch": 20.789419288979843, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14543095231056213, "target_z": -0.5234374843448509, "ce": 5.911416053771973, "genuineness": 4.262581825256348, "identity": 0.597523033618927, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/3dca9a4cdb77a9e6ea3c68f97da7d062453b5c933e0727bcccf9ca41c690e71d.mp3" }, { "id": "emo_Impatience_and_Irritability-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-1", "key": "3df718d4c1f79cb18706eaf4ed474f1b6306e99285464a25be6d3d21dd921ebe", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "7c96f62974495cea00c9c1e88b9a8287cc1a84fe029689c96a96d2822c59a386", "generation_seconds_batch": 19.48980699502863, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13474136590957642, "target_z": -0.5390624884288029, "ce": 6.054384231567383, "genuineness": 4.2374773025512695, "identity": 0.4861384630203247, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/3df718d4c1f79cb18706eaf4ed474f1b6306e99285464a25be6d3d21dd921ebe.mp3" }, { "id": "emo_Impatience_and_Irritability-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-1", "key": "3e6074be9a8acbba6abd5bec225bb3754a524ba9e20331cc35fdeac64f509fab", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] He encontrado la cajita.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "6f909e049de8c366cddd25d4fc09b3b3cf6bf57e0cf3c314ec9ee301920ca3a1", "generation_seconds_batch": 13.185169397038408, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4126705229282379, "target_z": -0.13281251293251448, "ce": 5.689021587371826, "genuineness": 4.15588903427124, "identity": 0.43600907921791077, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/3e6074be9a8acbba6abd5bec225bb3754a524ba9e20331cc35fdeac64f509fab.mp3" }, { "id": "emo_Impatience_and_Irritability-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-0", "key": "3e8b0c4a4851d77afff66044087c8d9aa3900c49e1958797f9e9560359506d21", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La puerta sigue abierta.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "306db251dea6c2fd85d10b699e9693966e357ffd88d3cedb145476ce0922b708", "generation_seconds_batch": 20.710262104985304, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2523267865180969, "target_z": -0.36718748706748555, "ce": 6.078212261199951, "genuineness": 4.331617832183838, "identity": 0.45167919993400574, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/3e8b0c4a4851d77afff66044087c8d9aa3900c49e1958797f9e9560359506d21.mp3" }, { "id": "emo_Impatience_and_Irritability-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-1", "key": "3ea7e40aed9cec041d021151b2f8a51b8319578b118719c89d0ad8c2f1e1a2de", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] He encontrado la cajita.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "53416cb8876c5bbe4106cd5067a1b4cc4366054d2d725e623d4319f085b8fa94", "generation_seconds_batch": 18.300851456006058, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1240517795085907, "target_z": -0.5546874925127547, "ce": 6.09409761428833, "genuineness": 4.532451152801514, "identity": 0.6063276529312134, "hypothesis": "He encontrado la cajita, estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/3ea7e40aed9cec041d021151b2f8a51b8319578b118719c89d0ad8c2f1e1a2de.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-0", "key": "3eefe7badf0473e18a9e7f477ad1a0ba282d71155a6d07864350ca15a36d393c", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La porte est encore ouverte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "9532327f50d97b84a547d1055b9b3ce928d0da3bbeaf566eb7a4c15fd10182ae", "generation_seconds_batch": 17.8829025629675, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.30711090564727783, "target_z": -0.2871093574730396, "ce": 5.879645347595215, "genuineness": 4.381826400756836, "identity": 0.2386772334575653, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/3eefe7badf0473e18a9e7f477ad1a0ba282d71155a6d07864350ca15a36d393c.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-1", "key": "3f407265bc7da1093ad2d0879e96a619b8f619a65b54b18613baef8e85132822", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "4e773709a0dfbdf9d59b71b1993408e7d331a9bb35e24ea7c1e1e9fa9979860f", "generation_seconds_batch": 19.404811788001098, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.791102886199951, "target_z": 3.3437500027226346, "ce": 6.229123115539551, "genuineness": 3.810706615447998, "identity": 0.40807658433914185, "hypothesis": "Ik 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_Impatience_and_Irritability/3f407265bc7da1093ad2d0879e96a619b8f619a65b54b18613baef8e85132822.mp3" }, { "id": "emo_Impatience_and_Irritability-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-1", "key": "3ff932a749e4e8a298f18e998c79832b841736d3799bcfecd3d914740c975dc7", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] He encontrado la cajita.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "35d073cc7dd9875e1e9ae32232c33591a1a4b027c6bdf18d098398170082cf2e", "generation_seconds_batch": 17.819966171053238, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03319031000137329, "target_z": -0.6875000054452692, "ce": 6.157639026641846, "genuineness": 4.6956281661987305, "identity": 0.6457648277282715, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/3ff932a749e4e8a298f18e998c79832b841736d3799bcfecd3d914740c975dc7.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": "4017b5309239b5744b82c0e9340c47357a1d7e82f3c3dd1ad42c4c6a2d7857ca", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "8dbab04f8d330a5b4053a8032a5317cfb445e4dc40319693eed70e963ef06b2a", "generation_seconds_batch": 21.12665927200578, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1438591480255127, "target_z": 3.8593750068065864, "ce": 5.756534099578857, "genuineness": 3.500042676925659, "identity": 0.06615001708269119, "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": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/4017b5309239b5744b82c0e9340c47357a1d7e82f3c3dd1ad42c4c6a2d7857ca.mp3" }, { "id": "emo_Impatience_and_Irritability-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-0", "key": "404c0a56a61228cca18363f1b7386547e4b555ff497de0e8a4129134accce18c", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La puerta sigue abierta.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "d6c69cf60639c39235e8394988900a61026c67013bcb859194dec6b7f38198d2", "generation_seconds_batch": 19.554008167004213, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2790507376194, "target_z": -0.32812499863868266, "ce": 6.006728172302246, "genuineness": 4.519899368286133, "identity": 0.31045955419540405, "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_Impatience_and_Irritability/404c0a56a61228cca18363f1b7386547e4b555ff497de0e8a4129134accce18c.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-1", "key": "40765828eef093f1f4fba28b9368de4974fd667ddb067a4b6ad8ed1954e7b249", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "418c88b8c998b31803e3fed6ac6d20f602c6b6f248f2916617a33e5410218a45", "generation_seconds_batch": 17.861022870987654, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6364836692810059, "target_z": 0.1943359093377481, "ce": 6.09409761428833, "genuineness": 4.042920112609863, "identity": 0.5809651613235474, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/40765828eef093f1f4fba28b9368de4974fd667ddb067a4b6ad8ed1954e7b249.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": "40b5471e81690214c915174fc77a87fa3793068d05434fb0c8ddd2703736c420", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "49db695fef01488f27e92e8d5965cb24fa97d294eeb2e103b8d08694088a1cdf", "generation_seconds_batch": 13.313538247020915, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3314507007598877, "target_z": 2.671874870674855, "ce": 5.990842819213867, "genuineness": 3.810706615447998, "identity": 0.5533069968223572, "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_Impatience_and_Irritability/40b5471e81690214c915174fc77a87fa3793068d05434fb0c8ddd2703736c420.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-1", "key": "40b91cf082ff5e37951fa0bde1018074a538d80d4b1ae60f43eb8323e6a69736", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "46c2527e15c4076aad566f89769566d9f24601e0dacda61d060ed065a21f3b03", "generation_seconds_batch": 18.121481977053918, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6852549314498901, "target_z": 0.26562502586502895, "ce": 6.149696350097656, "genuineness": 4.2249250411987305, "identity": 0.7602025270462036, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/40b91cf082ff5e37951fa0bde1018074a538d80d4b1ae60f43eb8323e6a69736.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-0", "key": "40ea0cb4f921a1eec677255fbd2c1e993419104ae0c527c46818a22afd330ef6", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De deur staat nog open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "9c6bb6479b2312a4ace6dfee69f24041377fb10ef97aeb28b3c9ca89464f6fb0", "generation_seconds_batch": 19.551935908966698, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2945611476898193, "target_z": 1.1562499537152113, "ce": 5.847874641418457, "genuineness": 3.6914620399475098, "identity": 0.43039724230766296, "hypothesis": "De deur 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_Impatience_and_Irritability/40ea0cb4f921a1eec677255fbd2c1e993419104ae0c527c46818a22afd330ef6.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": "40ed8c2a047f03f520c962caab1dcf75a15e5bef6ae0b0d70b7fa2ad769c484a", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b0d380eccf4351d9aac1fd8984b52bcd56df6548c4fe2cc85c8814520496e993", "generation_seconds_batch": 13.158372025936842, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2090444564819336, "target_z": 1.031249921043596, "ce": 5.657250881195068, "genuineness": 4.005263805389404, "identity": 0.3289256691932678, "hypothesis": "Ich schrieb die Nummer auf den Umschlag, rieß sie genau und prüfe die letzten beiden Ziffern. Ruf an, wenn du Zeit hast.", "wer": 0.045454545454545456, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/40ed8c2a047f03f520c962caab1dcf75a15e5bef6ae0b0d70b7fa2ad769c484a.mp3" }, { "id": "emo_Impatience_and_Irritability-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-1", "key": "4103d799997e081ccd747a7114776d3a923d1c6c5d17e80beb4a3d6af8d14f03", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] He encontrado la cajita.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "2bbdc05c52663cdc08d1184ab595a45c21fb72d39fa71ae9acdbcd9b42518941", "generation_seconds_batch": 13.185169397038408, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1240517795085907, "target_z": -0.5546874925127547, "ce": 5.9431867599487305, "genuineness": 4.381826400756836, "identity": 0.6257007718086243, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/4103d799997e081ccd747a7114776d3a923d1c6c5d17e80beb4a3d6af8d14f03.mp3" }, { "id": "emo_Impatience_and_Irritability-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-1", "key": "413e13dc58d3d22c8380c087dcf33e261d89e10c7d432f9815df1a43fc3f708c", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I found the little box.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "1474e23168a7713ee1c6f83f4dd69537fbf90b7d660553fc9ca211025f798bcb", "generation_seconds_batch": 18.831526429974474, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0251731276512146, "target_z": -0.6992187476176948, "ce": 6.086154937744141, "genuineness": 4.030367851257324, "identity": 0.34965986013412476, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/413e13dc58d3d22c8380c087dcf33e261d89e10c7d432f9815df1a43fc3f708c.mp3" }, { "id": "emo_Impatience_and_Irritability-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-1", "key": "4163cfcade98fa953869a20caccc4c6fcf0e60dae75f1246434f4ab01ef7a7cd", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I found the little box.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "6944df13b3d2414f1d9efa5be0c5e6453a0212322b684b0f9716d827b589a48f", "generation_seconds_batch": 18.120794444927014, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.41534292697906494, "target_z": -0.128906251020988, "ce": 5.506340026855469, "genuineness": 3.3870739936828613, "identity": 0.5002464056015015, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/4163cfcade98fa953869a20caccc4c6fcf0e60dae75f1246434f4ab01ef7a7cd.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-0", "key": "41907249feae99ff5e23c532ee471e399b7f02f4a8d8e26280e15a4d12f8529e", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La porte est encore ouverte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "4aed7152b6445bafec1d7667e4152ab78cec52ffccbf6bb0e81b5639846363ef", "generation_seconds_batch": 17.954309733002447, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.32581764459609985, "target_z": -0.2597656547788162, "ce": 5.434855937957764, "genuineness": 4.293961524963379, "identity": 0.4828992486000061, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/41907249feae99ff5e23c532ee471e399b7f02f4a8d8e26280e15a4d12f8529e.mp3" }, { "id": "emo_Impatience_and_Irritability-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-1", "key": "4197fa4f202392257cc97681917dd00e56a2a79178723744f3b4aae75708e8a8", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I found the little box.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "a0d5bf965219aaa6ecc0a3b347ec3054906823bf0f66b1a6198e597f5ebc4513", "generation_seconds_batch": 17.882239539991133, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0469815731048584, "target_z": -0.8046875142938318, "ce": 6.356205940246582, "genuineness": 4.65797233581543, "identity": 0.3325502872467041, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/4197fa4f202392257cc97681917dd00e56a2a79178723744f3b4aae75708e8a8.mp3" }, { "id": "emo_Impatience_and_Irritability-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-0", "key": "41b818c3d52c9055f7055613da114255cfdd9e29d5bbe6d247e95e315b0480be", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Tür ist noch offen.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "6396b0f323163517d6a97952d47c0c4c89f3e762710e1969de610a313aea8c40", "generation_seconds_batch": 20.065921458997764, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.6462695598602295, "target_z": 4.593749980941558, "ce": 5.242246150970459, "genuineness": 3.6098732948303223, "identity": 0.2517234683036804, "hypothesis": "Die Tür ist noch offen. Ich hab dein Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist!", "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_Impatience_and_Irritability/41b818c3d52c9055f7055613da114255cfdd9e29d5bbe6d247e95e315b0480be.mp3" }, { "id": "emo_Impatience_and_Irritability-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-0", "key": "41f3ada2992d4f992cc5bafdb3fb27937837413248cb244c65eb3831876a89e7", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La puerta sigue abierta.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "db9457b4bac73773cca23e0c6cb64e2a8daed7a789e899bad3912d4536fc8a3e", "generation_seconds_batch": 13.037632800056599, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2055598497390747, "target_z": -0.435546874489506, "ce": 5.720792293548584, "genuineness": 4.337893962860107, "identity": 0.5712165832519531, "hypothesis": "La puerta sigue abierta. He dejado tu abruigo 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_Impatience_and_Irritability/41f3ada2992d4f992cc5bafdb3fb27937837413248cb244c65eb3831876a89e7.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-1", "key": "421e36914c4d926fe8e829da63cf3e8de34d01dfda00acfb40894b247116653e", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "f57ebc685a513ed2bb401f303b696963ce27f213804f99b172ab57ce6c822761", "generation_seconds_batch": 18.262310496065766, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08129343390464783, "target_z": -0.6171875088485625, "ce": 6.141753673553467, "genuineness": 4.519899368286133, "identity": 0.70652836561203, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/421e36914c4d926fe8e829da63cf3e8de34d01dfda00acfb40894b247116653e.mp3" }, { "id": "emo_Impatience_and_Irritability-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-0", "key": "4239509e3b50cff930c9f25bd94d15d7cf0e6a3bd60f6a42e2732c72384bd7d5", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La puerta sigue abierta.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6415eea5cfb9b1d296548702eb91d3f7e14e9984ff5db90f1ced928907b44f26", "generation_seconds_batch": 18.175981712993234, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15612053871154785, "target_z": -0.507812480260899, "ce": 6.0305562019348145, "genuineness": 4.444586753845215, "identity": 0.428375244140625, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/4239509e3b50cff930c9f25bd94d15d7cf0e6a3bd60f6a42e2732c72384bd7d5.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_Impatience_and_Irritability", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": "62b46a7a159939ccdd98a509324e91b173782c4f4f21af35196b12de000c6d23", "generation_seconds_batch": 13.2070917369565, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19086167216300964, "target_z": -0.4570312496596707, "ce": 6.141753673553467, "genuineness": 4.432034492492676, "identity": 0.8161094188690186, "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_Impatience_and_Irritability/434f953004ee3838b31e4f505ba0cb9202b34ab37936979fff50edb64a6a996f.mp3" }, { "id": "emo_Impatience_and_Irritability-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-0", "key": "43554ba5f19e602f6b8662c50716423b44d1f10fbdad06fd16f902cabd00492a", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La puerta sigue abierta.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "00eec82449829cae0594d1f0ab6342f4413000fda4a0e2fbcc2264608c918c32", "generation_seconds_batch": 18.05922950198874, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7483444213867188, "target_z": 3.2812498121382108, "ce": 5.470598220825195, "genuineness": 3.525146961212158, "identity": 0.6835324168205261, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/43554ba5f19e602f6b8662c50716423b44d1f10fbdad06fd16f902cabd00492a.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_Impatience_and_Irritability", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": "3f79d92c05bcada2eff3afba7f063c89b1856545ee03ede5ee9daaac08403aff", "generation_seconds_batch": 13.553846615948714, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.116034597158432, "target_z": -0.5664062346851803, "ce": 6.173524379730225, "genuineness": 4.406930446624756, "identity": 0.5372664928436279, "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_Impatience_and_Irritability/43d771a5c055e2aea1186dc99f4cdef2b4c6bc8c6b2779ad35a29ca11c75a91c.mp3" }, { "id": "emo_Impatience_and_Irritability-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-0", "key": "44567eae47d924f5af5673a67476f3b00ef3136dd21e6b7dd102a31fe39be517", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Tür ist noch offen.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "f57a3d8b252055fd8a9450755de1e5984fee6e31bd7727519cf593f47466f9e7", "generation_seconds_batch": 23.132250800030306, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4066576361656189, "target_z": -0.14160156956183356, "ce": 6.308549880981445, "genuineness": 4.808597087860107, "identity": 0.5657349824905396, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/44567eae47d924f5af5673a67476f3b00ef3136dd21e6b7dd102a31fe39be517.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-1", "key": "446d7c2450764dcada1b580d7a6ec3c4bb357de2c2d04706b36dc42e39e296c6", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "8050823db37953c402efb11d42ab37e3771b20ce12bd36866bcdd52b7c914a51", "generation_seconds_batch": 19.82584500091616, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08663824200630188, "target_z": -0.6093749850255096, "ce": 6.038498878479004, "genuineness": 4.570107460021973, "identity": 0.541867733001709, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/446d7c2450764dcada1b580d7a6ec3c4bb357de2c2d04706b36dc42e39e296c6.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-0", "key": "44934fb45fd21e7621b7db7680a206f1cbf085f7b6857ed8f64bcada8aabcffd", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De deur staat nog open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "1b6135ec39811c64aab6693efe53b40c6417aff2c1d98b91c5dad570fb70eb04", "generation_seconds_batch": 14.112069704104215, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.897998571395874, "target_z": 3.49999978218923, "ce": 5.569881439208984, "genuineness": 3.600459337234497, "identity": 0.20450228452682495, "hypothesis": "De deur 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_Impatience_and_Irritability/44934fb45fd21e7621b7db7680a206f1cbf085f7b6857ed8f64bcada8aabcffd.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-1", "key": "4552cd5cd998d33dfc733bd689f9e97e4fa318e79d7c0bb84ca593d963038a52", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "a307e2fa362b4711383bdadf01bc262295df7a6ef9a06c5f5bc018e1273760a0", "generation_seconds_batch": 19.338804801926017, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8001679182052612, "target_z": 0.43359372175266575, "ce": 5.728734970092773, "genuineness": 4.124508857727051, "identity": 0.7071279287338257, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/4552cd5cd998d33dfc733bd689f9e97e4fa318e79d7c0bb84ca593d963038a52.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": "45670649e56a2c43f0cec074e6b137a4242862767165e95b01dd2d2f619a8e98", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2ae4345d3e31386ea29902abfce7cb782ddf735d1874fc52094ce2dddc3e064a", "generation_seconds_batch": 18.904618831002153, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.823171615600586, "target_z": 3.3906249714123367, "ce": 5.990842819213867, "genuineness": 3.7793264389038086, "identity": 0.6311727166175842, "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_Impatience_and_Irritability/45670649e56a2c43f0cec074e6b137a4242862767165e95b01dd2d2f619a8e98.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": "45683c664291d9fa24190e59171395c907ae12501a765d2b6de1190cf97bde7a", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e9a50c1882b56ee6c88e5cdaa782f5172c6ab90c10eff62308011e8d20216614", "generation_seconds_batch": 19.03112119191792, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1069695949554443, "target_z": 2.3437500898469428, "ce": 5.474569320678711, "genuineness": 3.553389072418213, "identity": 0.29216480255126953, "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_Impatience_and_Irritability/45683c664291d9fa24190e59171395c907ae12501a765d2b6de1190cf97bde7a.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": "45b3255ada75b66bbf5c254f2f8cf16739e19dca121878ce4236bbd80486e523", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "4e9a0eb08efb0082869e263f12932fb3cb038179a78ffac537850dcdc736edfd", "generation_seconds_batch": 14.762608028016984, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4169673919677734, "target_z": 2.796874903346471, "ce": 5.43088436126709, "genuineness": 3.7918784618377686, "identity": 0.6201885938644409, "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_Impatience_and_Irritability/45b3255ada75b66bbf5c254f2f8cf16739e19dca121878ce4236bbd80486e523.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_Impatience_and_Irritability", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": "60e0c8d2405671d3fd85c243258b827ec056ba7e9eea77b6fe5ccf4c03b03cad", "generation_seconds_batch": 13.1396693889983, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.116034597158432, "target_z": -0.5664062346851803, "ce": 6.38003396987915, "genuineness": 4.494794845581055, "identity": 0.5653713345527649, "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_Impatience_and_Irritability/45f9ec8497c8691f9e18d794cf98f47c522bfab041b36df5accabf5c5c456412.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-0", "key": "4634ba6a059ef7ef45cfeeb73000e7dc5e8822842eec2c220ccf8d5cfc8594a7", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De deur staat nog open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "7ac49f1a532f688543594bd0f738950da614037da356383ac6275cafbf74c43b", "generation_seconds_batch": 18.489454717026092, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.571678102016449, "target_z": 0.09960939558992435, "ce": 5.8875885009765625, "genuineness": 4.193545341491699, "identity": 0.5085887312889099, "hypothesis": "De deur 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_Impatience_and_Irritability/4634ba6a059ef7ef45cfeeb73000e7dc5e8822842eec2c220ccf8d5cfc8594a7.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": "465a8943923f9b982911713d24dda8b7ebe15834062593cb48fb3d598c20c91e", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b7794f2fa63d87cf3a52bba1c18724396ee00b2e143dfd2aeddf85d67018ffeb", "generation_seconds_batch": 19.720723379054107, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9145569801330566, "target_z": 2.0624999292114996, "ce": 5.982900142669678, "genuineness": 3.7416701316833496, "identity": 0.6229415535926819, "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_Impatience_and_Irritability/465a8943923f9b982911713d24dda8b7ebe15834062593cb48fb3d598c20c91e.mp3" }, { "id": "emo_Impatience_and_Irritability-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-0", "key": "46a8fbba9b3986a2163aef56340cbf9e4841706ca5edd33ed7bc88e75e327f3d", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Tür ist noch offen.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "5e0ccab9705fbde4eadc71709770b77c908a8898717e4ac06846695afba3a5c4", "generation_seconds_batch": 13.132569657987915, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5618007183074951, "target_z": 1.5468749251275478, "ce": 5.458683967590332, "genuineness": 3.9299514293670654, "identity": 0.37626945972442627, "hypothesis": "Die Tür ist noch offen. Ich habe dein Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/46a8fbba9b3986a2163aef56340cbf9e4841706ca5edd33ed7bc88e75e327f3d.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-0", "key": "470a0f975262efac47986232873ddabc4681fc174f5d7d24dd241213a1ddeb6c", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La porte est encore ouverte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "2dd9498f172b1e5e229d84b3618cdc066bf3ae09d5b1ed27e29d5c7c89ce5ed4", "generation_seconds_batch": 13.465286222985014, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2496543824672699, "target_z": -0.37109374897901204, "ce": 6.046441555023193, "genuineness": 4.432034492492676, "identity": 0.5791776180267334, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/470a0f975262efac47986232873ddabc4681fc174f5d7d24dd241213a1ddeb6c.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-1", "key": "473b1d9995fbc00767cfd91e9fca8cfbb8eb86a759be2dbae6fc2d1437c4a67d", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "20b6c1cc24c0a2665262d193aeba4a41f0e086ab98592ac7ab75f144ad6c567b", "generation_seconds_batch": 19.40244674193673, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5168939828872681, "target_z": 0.01953126599547842, "ce": 6.0146708488464355, "genuineness": 4.20609712600708, "identity": 0.6635018587112427, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/473b1d9995fbc00767cfd91e9fca8cfbb8eb86a759be2dbae6fc2d1437c4a67d.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-1", "key": "47bf47941f74ad379ffe1108b0f42abe1cabc751af972ea2a850bc8b45da1988", "bucket": "emo_Impatience_and_Irritability", "phase": "wording", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "9b2df3c2da2cfca5e4c2845356f0d37827f274cd70f3e2f69d7dd2ac603290fe", "generation_seconds_batch": 14.222604966023937, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2042236626148224, "target_z": -0.43749998366419224, "ce": 6.213237762451172, "genuineness": 4.532451152801514, "identity": 0.6010738015174866, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/47bf47941f74ad379ffe1108b0f42abe1cabc751af972ea2a850bc8b45da1988.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_Impatience_and_Irritability", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": "817e8fcb5a6c6300d831e2e18e72a564fc1424ddfa8902b9ea045dab6afa0c2c", "generation_seconds_batch": 13.300566393998452, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10801738500595093, "target_z": -0.5781250204197597, "ce": 6.268836498260498, "genuineness": 4.582659721374512, "identity": 0.7966099977493286, "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_Impatience_and_Irritability/47d00b404f769e82194cfb39f2be7a6bd3cc5bfaac4f38356b0fada2abdb9f4d.mp3" }, { "id": "emo_Impatience_and_Irritability-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-0", "key": "47eb69992dd34f47c68a780945d19b4510d6561cdb5c7c563f7ed160bee9ded4", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Tür ist noch offen.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "8122ecb3cf1e45572fb766d3bdf68932809025bc3d01a9884fe27594126c744e", "generation_seconds_batch": 19.385278019937687, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5297319889068604, "target_z": 1.499999956437846, "ce": 5.816103935241699, "genuineness": 4.256305694580078, "identity": 0.2767835557460785, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/47eb69992dd34f47c68a780945d19b4510d6561cdb5c7c563f7ed160bee9ded4.mp3" }, { "id": "emo_Impatience_and_Irritability-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-0", "key": "4882e0a0c8999567369e56cd06519f35bb8825d80ba77515d9dfd4ec261b3bfb", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La puerta sigue abierta.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "63abe1fa11a9d11793545000c57d25bc27db9d5a50a894b9f7cf6c3cacd8a6d3", "generation_seconds_batch": 18.13834633899387, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07060384750366211, "target_z": -0.6328125129325145, "ce": 6.038498878479004, "genuineness": 4.256305694580078, "identity": 0.5001237392425537, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/4882e0a0c8999567369e56cd06519f35bb8825d80ba77515d9dfd4ec261b3bfb.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-0", "key": "488376057f60053e471ea59ef2a8b82bba759bd0b8c132fd395fcdaca2db6639", "bucket": "emo_Impatience_and_Irritability", "phase": "wording", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De deur staat nog open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "81861d4b97ce213908e8cd05d2025f24966305ac22f0b258a7459417887073ac", "generation_seconds_batch": 14.2863726610085, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16146531701087952, "target_z": -0.5, "ce": 6.046441555023193, "genuineness": 4.15588903427124, "identity": 0.6875963807106018, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/488376057f60053e471ea59ef2a8b82bba759bd0b8c132fd395fcdaca2db6639.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-0", "key": "4979982dc001b90d763cfe7c7a63210b1a55e8b1861cacf88cf0b41962f05104", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De deur staat nog open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "313f6e10517fc63142e0d4d8cfd6d3c9667a0a5ee4015fab0988e8fad5627921", "generation_seconds_batch": 13.21820282691624, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0861142873764038, "target_z": 0.8515624829835335, "ce": 6.078212261199951, "genuineness": 4.20609712600708, "identity": 0.4922262132167816, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/4979982dc001b90d763cfe7c7a63210b1a55e8b1861cacf88cf0b41962f05104.mp3" }, { "id": "emo_Impatience_and_Irritability-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-0", "key": "49a97d56667d2059ff360c4a06f5a2e53f37860d282972d3a5db631717e84b8a", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The door is still open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "5ecf966f6bf998979408155783b3e5202f5f1a357bb25a8a5de140d7eb0ed016", "generation_seconds_batch": 18.098767507006414, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3378434479236603, "target_z": -0.24218749795802402, "ce": 6.078212261199951, "genuineness": 3.9927117824554443, "identity": 0.30687737464904785, "hypothesis": "The 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_Impatience_and_Irritability/49a97d56667d2059ff360c4a06f5a2e53f37860d282972d3a5db631717e84b8a.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_Impatience_and_Irritability", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fccc0ec445039984a07f95b884d26cffb4ab83aca537e147a6d95f3614364d44", "generation_seconds_batch": 13.278927120030858, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07327625155448914, "target_z": -0.628906251020988, "ce": 6.078212261199951, "genuineness": 3.9927117824554443, "identity": 0.6983241438865662, "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_Impatience_and_Irritability/49d468ae6540cc7c1e5b0e6883c25e2b29599458c9de0a5398000eaca62677ab.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-0", "key": "4adc5cfb6c3a8a43fe09be2dcc63d4c60ca41428c475d2cd51aff97c6005fcf9", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La porte est encore ouverte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "005a58a409766e48eb4749de3dcbdce6356c8d9837b0d2acf0dce034e486fc4a", "generation_seconds_batch": 19.042664563981816, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22560280561447144, "target_z": -0.4062500190584424, "ce": 5.974957466125488, "genuineness": 4.174716949462891, "identity": 0.5185673832893372, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/4adc5cfb6c3a8a43fe09be2dcc63d4c60ca41428c475d2cd51aff97c6005fcf9.mp3" }, { "id": "emo_Impatience_and_Irritability-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-0", "key": "4af51b31aa229cad45baaf5d1933cefe2feef33db1461ab9e12a5911f1cb0b82", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La puerta sigue abierta.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "64fa70ea2bf029b13695a27b5c298ea4c15c240cd33d346ae8fadc641301d095", "generation_seconds_batch": 20.300041173002683, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5131735801696777, "target_z": 2.937499809415576, "ce": 5.276002407073975, "genuineness": 3.5816311836242676, "identity": 0.6263541579246521, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/4af51b31aa229cad45baaf5d1933cefe2feef33db1461ab9e12a5911f1cb0b82.mp3" }, { "id": "emo_Impatience_and_Irritability-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-1", "key": "4b3253743952a3bb2c88d00e57f71e5712a7d95c66068191a064298dbd701720", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I found the little box.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "3b40a8daa9d8a27933dbc1bcfa74a34ddbb5ac4771c5bcdebefc4accbf0ed205", "generation_seconds_batch": 13.142973654088564, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.014912784099578857, "target_z": -0.7578124584798219, "ce": 6.157639026641846, "genuineness": 4.293961524963379, "identity": 0.5677855014801025, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/4b3253743952a3bb2c88d00e57f71e5712a7d95c66068191a064298dbd701720.mp3" }, { "id": "emo_Impatience_and_Irritability-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-0", "key": "4c9a4c65d76792d3e7d7e6d506c063c8e16df1a89eef1cae53e524a05afe7126", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The door is still open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "f3b5b5da2aa7a585452470e3c6f2a0386c1c5e3e165d8a2d037aad64fce74a9b", "generation_seconds_batch": 18.124187557958066, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11336219310760498, "target_z": -0.5703124965967067, "ce": 6.292664527893066, "genuineness": 4.005263805389404, "identity": 0.18529535830020905, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/4c9a4c65d76792d3e7d7e6d506c063c8e16df1a89eef1cae53e524a05afe7126.mp3" }, { "id": "emo_Impatience_and_Irritability-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-0", "key": "4d75baa9e32a8496c9661ce9be1e769fc65fa8c19686aaa1054bfbb01a8a43eb", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Tür ist noch offen.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "fa7fbe3dceaaba98f800774b577fa9d74df57678dee27f891f5f90509a741756", "generation_seconds_batch": 18.891891437000595, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.33383485674858093, "target_z": -0.24804686904423676, "ce": 6.078212261199951, "genuineness": 4.413206577301025, "identity": 0.3842998445034027, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/4d75baa9e32a8496c9661ce9be1e769fc65fa8c19686aaa1054bfbb01a8a43eb.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-1", "key": "4dac21e72abcc3cee782dae725089f8bee3aee0d39bcde69c54582fd68161489", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "dc0e2ba3c862ccccc680dc10b1500119739c59b39d74841e952723a3ba91ee6b", "generation_seconds_batch": 13.508732515969314, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.012240409851074219, "target_z": -0.7539062401304495, "ce": 5.959072113037109, "genuineness": 4.369274139404297, "identity": 0.6433305740356445, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/4dac21e72abcc3cee782dae725089f8bee3aee0d39bcde69c54582fd68161489.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-1", "key": "4dc637abee73c787cd2ed0c9441273717773f5e87231c1fdc5c75cde9fe14c17", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "7f7a8f8bad5fde33246b8e65fd39ddc516fda589e1c29da2b22bb71c445ac405", "generation_seconds_batch": 18.09051540098153, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5863762497901917, "target_z": 0.12109372719793501, "ce": 6.1894097328186035, "genuineness": 3.9425034523010254, "identity": 0.6937906742095947, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/4dc637abee73c787cd2ed0c9441273717773f5e87231c1fdc5c75cde9fe14c17.mp3" }, { "id": "emo_Impatience_and_Irritability-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-0", "key": "4df7a9fabb0b1ab262fcba2e549cef7086f997effeaa970810818ac322cd70ce", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The door is still open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "d86bad9c7a0c60dd9c0e4250bb45125bc4f6bd5f0149d8da9e26b658c372febc", "generation_seconds_batch": 17.91326364199631, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5773110389709473, "target_z": 3.03124974679498, "ce": 6.268836498260498, "genuineness": 3.7416701316833496, "identity": 0.5308263897895813, "hypothesis": "The 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_Impatience_and_Irritability/4df7a9fabb0b1ab262fcba2e549cef7086f997effeaa970810818ac322cd70ce.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": "4e5b442547b5abb8e4e33d1af8233ae37a37d78e1ce409a407ccd873dbc33849", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f7d92ab36501ac0f9dcdc1c0288b6cd28709bde9ba4435baf3611120b8a74d29", "generation_seconds_batch": 14.762608028016984, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4121465682983398, "target_z": 1.3281249550765286, "ce": 5.649308204650879, "genuineness": 3.7793264389038086, "identity": 0.671214759349823, "hypothesis": "Las llaves están en la mesa de la cocina. Mire en el cajón y luego, junto a la ventana, llévatelas cuando te vayas.", "wer": 0.043478260869565216, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/4e5b442547b5abb8e4e33d1af8233ae37a37d78e1ce409a407ccd873dbc33849.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-0", "key": "4e76d327cf86e48d12a51f45139ff313c9a1d38e4f853e9f4a93bef33f7e23ac", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De deur staat nog open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "f9cd63c5f5ee92d0bdce5cc05b695ebc6156db01feeb2e28efcb0fd939c19df4", "generation_seconds_batch": 17.979140985989943, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4801485240459442, "target_z": -0.03417969371101024, "ce": 5.772419452667236, "genuineness": 4.193545341491699, "identity": 0.5337733030319214, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/4e76d327cf86e48d12a51f45139ff313c9a1d38e4f853e9f4a93bef33f7e23ac.mp3" }, { "id": "emo_Impatience_and_Irritability-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-1", "key": "4f26ee8b3909d9a76e2aa24a947f51610996812d0115f9a0340c744584bc14f5", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I found the little box.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "07a3e61f14de82777c161a9d96a15709acb13ab4b015150122175c688a862c65", "generation_seconds_batch": 18.119181509013288, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06793147325515747, "target_z": -0.6367187312818869, "ce": 6.078212261199951, "genuineness": 3.911123275756836, "identity": 0.4252519905567169, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/4f26ee8b3909d9a76e2aa24a947f51610996812d0115f9a0340c744584bc14f5.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": "4f48df1c28ccae2dbc03e0f4b18ed5b23fd784b765da93cf42bd4d51003449fc", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ee8bc46b8868e4277311e1f12764214081a8a22314aef579bbe2ecac8ad9f985", "generation_seconds_batch": 13.30133551300969, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3955883979797363, "target_z": 2.765625156551491, "ce": 5.274016857147217, "genuineness": 3.653805732727051, "identity": 0.3414992094039917, "hypothesis": "Die Schlüssel liegen auf dem Küchentisch. Ich suchte in der Schublade. Dan 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_Impatience_and_Irritability/4f48df1c28ccae2dbc03e0f4b18ed5b23fd784b765da93cf42bd4d51003449fc.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-0", "key": "4f637430b2c58b81a07768e9bf0c0e3cdeb1e7b1dbf6754114a4934273362d45", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La porte est encore ouverte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "e0b7414f5df6cbf40a44d2d260e2798848e334a9ba3a49f3d93fc0977f09f914", "generation_seconds_batch": 19.195472339051776, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18952548503875732, "target_z": -0.4589843588343569, "ce": 6.038498878479004, "genuineness": 4.457139015197754, "identity": 0.6791899800300598, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/4f637430b2c58b81a07768e9bf0c0e3cdeb1e7b1dbf6754114a4934273362d45.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-1", "key": "4fefc3d69e820c9198a3e05152da0987bed8ccead72d83fbcdab2372547c3e1a", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "ca6a3480e3aee0afd726a7f0cfbede82ca293dbfa921501c6eabe6f1e746f591", "generation_seconds_batch": 20.14855235198047, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6959444880485535, "target_z": 0.28124998638682686, "ce": 5.172747611999512, "genuineness": 4.042920112609863, "identity": 0.5693981647491455, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/4fefc3d69e820c9198a3e05152da0987bed8ccead72d83fbcdab2372547c3e1a.mp3" }, { "id": "emo_Impatience_and_Irritability-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-1", "key": "5021bf3ca8b5d3ef74561deec044a331b4e0abe5268e26926fe3005fe1f817de", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I found the little box.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "371ccf38ea2602aaee6e2d14c4b0d6a77a56bad6b59db4dc15339e1920be2876", "generation_seconds_batch": 14.606093233102001, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2229304313659668, "target_z": -0.41015623740781487, "ce": 5.816103935241699, "genuineness": 4.105680465698242, "identity": 0.3723602294921875, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/5021bf3ca8b5d3ef74561deec044a331b4e0abe5268e26926fe3005fe1f817de.mp3" }, { "id": "emo_Impatience_and_Irritability-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-0", "key": "50316016ae2aa94656286a0b32727e6492db02c70ef0815b5bf606124bece4da", "bucket": "emo_Impatience_and_Irritability", "phase": "wording", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La puerta sigue abierta.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "dd6291023c0ff581024e3b362438555bef88f08a3c32c9627667e61419d3eadc", "generation_seconds_batch": 15.41233797208406, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13741374015808105, "target_z": -0.5351562700794303, "ce": 5.77639102935791, "genuineness": 4.293961524963379, "identity": 0.7180162072181702, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/50316016ae2aa94656286a0b32727e6492db02c70ef0815b5bf606124bece4da.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-0", "key": "5031f6a771aee132056ff8cc7d8e27b783078a5a88d74dc42f878ef364b00abb", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La porte est encore ouverte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "e309107994abca3bfcb753c64faff27c343f415af2cfbfecc07d67aa73edeb73", "generation_seconds_batch": 19.242655509035103, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2566237449645996, "target_z": 2.5625000598979617, "ce": 6.038498878479004, "genuineness": 4.13078498840332, "identity": 0.5678436756134033, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/5031f6a771aee132056ff8cc7d8e27b783078a5a88d74dc42f878ef364b00abb.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-1", "key": "525617dede210b8c18f483c964682908aa193513d752281f0f2058f4cbaf78f6", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "c4f1a84b9ae5ccf41f1200aec3370bab0090ba1511ab62c183bfd9faf49f2b6e", "generation_seconds_batch": 18.499014214030467, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5356007218360901, "target_z": 0.04687496868970181, "ce": 6.157639026641846, "genuineness": 4.3504462242126465, "identity": 0.6771199703216553, "hypothesis": "J'ai trouvé la 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_Impatience_and_Irritability/525617dede210b8c18f483c964682908aa193513d752281f0f2058f4cbaf78f6.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-0", "key": "52de5c90593948b512a19bf0ba1db8d45d59e806466555586e48fee6f610e612", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La porte est encore ouverte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "90ac75006c5b1c2bc304c9a0b7d0e7975f2697ea5d93253c061fa71d8dc77f55", "generation_seconds_batch": 17.644325688946992, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5457663536071777, "target_z": 1.523437440782697, "ce": 6.348263263702393, "genuineness": 4.093128204345703, "identity": 0.6402186751365662, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/52de5c90593948b512a19bf0ba1db8d45d59e806466555586e48fee6f610e612.mp3" }, { "id": "emo_Impatience_and_Irritability-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-0", "key": "532d90347b35a4d80b6737afb6160944d20a735c05e47b9bbf142ba5546722b7", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La puerta sigue abierta.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "eefdd9cf0f23d3a17a5ffaa56f8d516f683ae7a0ebb661062330acac93a2cc3a", "generation_seconds_batch": 19.19352449697908, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.603511095046997, "target_z": 4.531249790357134, "ce": 5.526196479797363, "genuineness": 3.5941832065582275, "identity": 0.6459558010101318, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/532d90347b35a4d80b6737afb6160944d20a735c05e47b9bbf142ba5546722b7.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-1", "key": "535114bac038c34258ed7748c24ddc5e30e369ee638062869fd443580e529c59", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "5d37752cca0e9ae4ce0f4e5544acef1869c7721bf3037f846306c02bb45092e5", "generation_seconds_batch": 20.489676662022248, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05456948280334473, "target_z": -0.6562499972773653, "ce": 6.205295085906982, "genuineness": 4.7458367347717285, "identity": 0.7886835336685181, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/535114bac038c34258ed7748c24ddc5e30e369ee638062869fd443580e529c59.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-0", "key": "5366d64fd1ca47eba3b407d195b06f9612de63b1f779e400ce954ca40c9b41f6", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De deur staat nog open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "f46b1e567659d0c68d38c181c7e6fc737af97766e2a5edf312af2a6237fd223a", "generation_seconds_batch": 13.282106876024045, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9070637822151184, "target_z": 0.5898437625921852, "ce": 5.95112943649292, "genuineness": 3.948779582977295, "identity": 0.5205581188201904, "hypothesis": "De deur Hatic deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.10526315789473684, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/5366d64fd1ca47eba3b407d195b06f9612de63b1f779e400ce954ca40c9b41f6.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-1", "key": "53cce2e11b6b481557ff957c37afa2ada91f0545ef6c6bb63e6840cbad7d168f", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "cb2b292d16651535d2c51029567d01c560cc600c3f0a87ab49367cfedd54c7d6", "generation_seconds_batch": 19.234690356068313, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5511112213134766, "target_z": 1.5312500517300578, "ce": 5.498397350311279, "genuineness": 3.6287014484405518, "identity": 0.44809502363204956, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude ramen. 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_Impatience_and_Irritability/53cce2e11b6b481557ff957c37afa2ada91f0545ef6c6bb63e6840cbad7d168f.mp3" }, { "id": "emo_Impatience_and_Irritability-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-1", "key": "543147c7d4ef3650a3f5403a5c18d75fbdb05fa34ed0ec5b7932cd7bb03142e4", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I found the little box.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "99246e8942cfda1003af0e0e5a1e56f0d9bd52a0b385c5dc35880a4af2058694", "generation_seconds_batch": 19.697817581007257, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14543095231056213, "target_z": -0.5234374843448509, "ce": 5.6254801750183105, "genuineness": 3.8797430992126465, "identity": 0.6329602003097534, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/543147c7d4ef3650a3f5403a5c18d75fbdb05fa34ed0ec5b7932cd7bb03142e4.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_Impatience_and_Irritability", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": "84165452bb6b315c89abd050c65f8d9a507dcef30fd2f47c71c080db64da6235", "generation_seconds_batch": 13.1396693889983, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14008614420890808, "target_z": -0.5312500081679039, "ce": 6.443574905395508, "genuineness": 4.118232727050781, "identity": 0.447702020406723, "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_Impatience_and_Irritability/546203f143d2dbd908be3097fd76d41d76e93afd1487fa15c64a3d119dff5d49.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-1", "key": "5475ddd4e6096f32cb15d946885c1bfa62e5d87a213a2fd85b88fee77a8ed6e7", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "b4c12318757ab2c238bffc0810468393db97637ab85381eaee871d6e03f61a04", "generation_seconds_batch": 21.192283648997545, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6200695037841797, "target_z": 3.0937499373794037, "ce": 6.054384231567383, "genuineness": 3.6663577556610107, "identity": 0.33766335248947144, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/5475ddd4e6096f32cb15d946885c1bfa62e5d87a213a2fd85b88fee77a8ed6e7.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-0", "key": "54766787a35986c10fcc518ef9175b953fd9ff357bc3ae44a3f4a7afc6d13a57", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La porte est encore ouverte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "b8ecbb323096890ef66002b67c7118090618e964269d458ebe0bae260e39dd9f", "generation_seconds_batch": 19.844728477066383, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.3255820274353027, "target_z": 4.124999945547308, "ce": 5.756534099578857, "genuineness": 3.8169827461242676, "identity": 0.43781983852386475, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt ?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/54766787a35986c10fcc518ef9175b953fd9ff357bc3ae44a3f4a7afc6d13a57.mp3" }, { "id": "emo_Impatience_and_Irritability-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-0", "key": "5479294daafcd7277d7280aa7fac353202e3e6d968b0ec5466616f06b77ac201", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Tür ist noch offen.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "2ee39a63c2502f2d96ec29203d8657b204383ddc5b843d727d9f1d5f155f1925", "generation_seconds_batch": 18.087766544078477, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1069695949554443, "target_z": 2.3437500898469428, "ce": 6.141753673553467, "genuineness": 4.300237655639648, "identity": 0.4280011057853699, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/5479294daafcd7277d7280aa7fac353202e3e6d968b0ec5466616f06b77ac201.mp3" }, { "id": "emo_Impatience_and_Irritability-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-0", "key": "54813a9d166a5f05363eb152cd0f66c7210ff6e18942cf723c98e43a13ea5262", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La puerta sigue abierta.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "3e1f91bb83d7ffce4ee8ce2165e621ba76db93f254fabb2708049046d050e2ad", "generation_seconds_batch": 19.554008167004213, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1774996817111969, "target_z": -0.4765625156551491, "ce": 5.748591423034668, "genuineness": 4.256305694580078, "identity": 0.5334036350250244, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/54813a9d166a5f05363eb152cd0f66c7210ff6e18942cf723c98e43a13ea5262.mp3" }, { "id": "emo_Impatience_and_Irritability-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-1", "key": "54fecf55e8add073c35bc1e812532069a2f7516ccbe7b7328123bcfea6f3963d", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I found the little box.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "8a802e983117b49a899e870042c9154bfd3c12c5f5f41421ad09216bf325566e", "generation_seconds_batch": 18.18818409391679, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.07103312015533447, "target_z": -0.8398437408111081, "ce": 6.38797664642334, "genuineness": 4.6203155517578125, "identity": 0.4487532377243042, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/54fecf55e8add073c35bc1e812532069a2f7516ccbe7b7328123bcfea6f3963d.mp3" }, { "id": "emo_Impatience_and_Irritability-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-1", "key": "5506f22001a11003cd04dd59babdbed98ee987603417f785a8f94e5dfccd35b8", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] He encontrado la cajita.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "e2d65554222bd113d9074b0902d0a4adc1baf3287572c3320dc793f6a9faba4e", "generation_seconds_batch": 17.949045690940693, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.05767112970352173, "target_z": -0.8203124748156297, "ce": 6.125868320465088, "genuineness": 4.632867813110352, "identity": 0.60007643699646, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/5506f22001a11003cd04dd59babdbed98ee987603417f785a8f94e5dfccd35b8.mp3" }, { "id": "emo_Impatience_and_Irritability-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-1", "key": "5589f60ba696162d03d2229e18b176b7dab1da2725b4f589b90243f2c5b8e301", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I found the little box.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "4e7c47ed333f23d471678afbf205442ea6a933b74b6458fca74fb9b6207b7262", "generation_seconds_batch": 19.73026531690266, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05724188685417175, "target_z": -0.6523437353658389, "ce": 6.054384231567383, "genuineness": 4.193545341491699, "identity": 0.6038509607315063, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/5589f60ba696162d03d2229e18b176b7dab1da2725b4f589b90243f2c5b8e301.mp3" }, { "id": "emo_Impatience_and_Irritability-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-1", "key": "559ac2971f7dc46cc01bd5b95435e32ad075fa6fe6c9b944d21924615a90fdbb", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] He encontrado la cajita.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "d8e22601876cd39aa4559ab73fc564823b2a2ff34c21f5b08db98e4479fe001b", "generation_seconds_batch": 19.924960592063144, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2590077519416809, "target_z": -0.3574218976319003, "ce": 5.9431867599487305, "genuineness": 4.400654315948486, "identity": 0.6976463198661804, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/559ac2971f7dc46cc01bd5b95435e32ad075fa6fe6c9b944d21924615a90fdbb.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-0", "key": "55eb238af9651ac36b7dfe4f515c232c77b7f882c4fcf2fe08d42ae95d95a0cb", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De deur staat nog open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "39436aabeb54e6826d5a242547c4de3d5c7e1c054ebeb8c7c246499a2a5af8a0", "generation_seconds_batch": 18.923114534001797, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5275835394859314, "target_z": 0.03515622651727636, "ce": 5.967014789581299, "genuineness": 4.243753433227539, "identity": 0.40520012378692627, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/55eb238af9651ac36b7dfe4f515c232c77b7f882c4fcf2fe08d42ae95d95a0cb.mp3" }, { "id": "emo_Impatience_and_Irritability-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-0", "key": "55f2976ddad528280406c99b672eae5064bc96acc5d4e1f207ca4e4558a78b0b", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La puerta sigue abierta.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "2bbac6723658862fbd956b674815c8a06190a49f9953e08d82e836f1d23cd1c2", "generation_seconds_batch": 14.374641500995494, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21224084496498108, "target_z": -0.42578124149176677, "ce": 6.0305562019348145, "genuineness": 4.1998209953308105, "identity": 0.6137234568595886, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/55f2976ddad528280406c99b672eae5064bc96acc5d4e1f207ca4e4558a78b0b.mp3" }, { "id": "emo_Impatience_and_Irritability-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-1", "key": "55f46c008e80f37bc229d962d36befa46f4199410abab00465733c886252f736", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] He encontrado la cajita.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "efd8dadd69e24567917ae03ba0059417c56a3e2034eda720a73df7c11c0d12a6", "generation_seconds_batch": 13.242934221983887, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.019828319549560547, "target_z": -0.7070312714407476, "ce": 5.990842819213867, "genuineness": 4.532451152801514, "identity": 0.6013766527175903, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/55f46c008e80f37bc229d962d36befa46f4199410abab00465733c886252f736.mp3" }, { "id": "emo_Impatience_and_Irritability-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-1", "key": "5637892bc4f3138c92f8bfa812a52ce8a5d3072253430f8d43754eb98a52bf85", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "5814476ae04c02f213aa2b1dac9cc287d798ccf986f8ec6e953f9f7bd7a56ee9", "generation_seconds_batch": 14.061288948985748, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5168939828872681, "target_z": 0.01953126599547842, "ce": 6.038498878479004, "genuineness": 4.093128204345703, "identity": 0.6291919946670532, "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_Impatience_and_Irritability/5637892bc4f3138c92f8bfa812a52ce8a5d3072253430f8d43754eb98a52bf85.mp3" }, { "id": "emo_Impatience_and_Irritability-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-0", "key": "563c3ae82b054939c69e035bc9fdcb5117fb4c59bb59e20e535255f0f3afe4ac", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The door is still open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "ac776690ffe354f9f3f4d07d59d41d374bd149b751de6ace8f16f86f0ea5f6ec", "generation_seconds_batch": 17.82554499001708, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.481104850769043, "target_z": 2.8906248407258746, "ce": 5.101263999938965, "genuineness": 3.3117613792419434, "identity": 0.4092504382133484, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/563c3ae82b054939c69e035bc9fdcb5117fb4c59bb59e20e535255f0f3afe4ac.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-0", "key": "568e7db1abec0913c12a7e70b9b023a6d2eb8e334156a4d8e78da5bcde09e326", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La porte est encore ouverte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "6c1c7d8a538416d970ace9783a3f89690cdd01782174757c737303d25c3fe594", "generation_seconds_batch": 19.073175708996132, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5609884858131409, "target_z": 0.08398434794381841, "ce": 6.0305562019348145, "genuineness": 4.068024158477783, "identity": 0.6237354874610901, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/568e7db1abec0913c12a7e70b9b023a6d2eb8e334156a4d8e78da5bcde09e326.mp3" }, { "id": "emo_Impatience_and_Irritability-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-1", "key": "569996d1044c5e264af832251d1f9383e848050847fc752f0a5882360f5e262e", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] He encontrado la cajita.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "cce02dc9683a94d1e730ec8d5ea50342a954cbfd708f38fea563299453de32bf", "generation_seconds_batch": 19.924960592063144, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2149132490158081, "target_z": -0.42187497958024034, "ce": 5.895530700683594, "genuineness": 4.287685871124268, "identity": 0.48012447357177734, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/569996d1044c5e264af832251d1f9383e848050847fc752f0a5882360f5e262e.mp3" }, { "id": "emo_Impatience_and_Irritability-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-0", "key": "56df8e73bf50d78634b21009e84efd98e19bf316933b07340805e3e503023c88", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La puerta sigue abierta.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "6def14098c0e86353477121feeee4db23cac9732083859f9912d4211185138f3", "generation_seconds_batch": 18.394722539000213, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7542133331298828, "target_z": 1.8281250857629907, "ce": 5.689021587371826, "genuineness": 3.5314228534698486, "identity": 0.4924837052822113, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/56df8e73bf50d78634b21009e84efd98e19bf316933b07340805e3e503023c88.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-1", "key": "56f948ecca14cf600a26daacd76f86da10c83516399f153d5df37769843f26da", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "1f1d23875edb891cc94b0b76bcc67000c1f5cccf2cdd1fa98226493d4bf64b26", "generation_seconds_batch": 13.07682791503612, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3373194932937622, "target_z": 1.2187499700510191, "ce": 5.220403671264648, "genuineness": 3.7542223930358887, "identity": 0.24495793879032135, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het. Auw. We kunnen er samen in kijken.", "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_Impatience_and_Irritability/56f948ecca14cf600a26daacd76f86da10c83516399f153d5df37769843f26da.mp3" }, { "id": "emo_Impatience_and_Irritability-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-1", "key": "570af1ccd6ec4aa35ce3a6d7946eb51575b6b308eac51dc8c4446589dc11d988", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I found the little box.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "2e72c1ffd9aada2ce551f7a171a99a8c4c2129f60a111bcd5254c232942057fb", "generation_seconds_batch": 18.332297736080363, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.06301593780517578, "target_z": -0.8281249986386827, "ce": 6.268836498260498, "genuineness": 4.325342178344727, "identity": 0.5556117296218872, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/570af1ccd6ec4aa35ce3a6d7946eb51575b6b308eac51dc8c4446589dc11d988.mp3" }, { "id": "emo_Impatience_and_Irritability-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-0", "key": "57239f47134943d8d6a9a8abbb84467946817c362378274b6e2d19553fc00511", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La puerta sigue abierta.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "99fe0739e6fb98ba75082e4e0d1f511460a5258d1ed8b50b325710246afdc520", "generation_seconds_batch": 17.981368934968486, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21624943614006042, "target_z": -0.41992187040555407, "ce": 6.0305562019348145, "genuineness": 4.18099308013916, "identity": 0.5446987152099609, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/57239f47134943d8d6a9a8abbb84467946817c362378274b6e2d19553fc00511.mp3" }, { "id": "emo_Impatience_and_Irritability-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-1", "key": "5749bba66171e44582b416e653e072dfb4be9f968896f713c4a0d90bde9d4c0c", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I found the little box.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "9245bce98b1c1eb6b84e39bc373985f142a9b5af0dd61192c47d9ba8354c431b", "generation_seconds_batch": 22.08885065105278, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3031023144721985, "target_z": -0.2929687285592523, "ce": 5.7684478759765625, "genuineness": 3.6914620399475098, "identity": 0.4909680187702179, "hypothesis": "I found the little box. It was beside the old window. We can look inside together", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/5749bba66171e44582b416e653e072dfb4be9f968896f713c4a0d90bde9d4c0c.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-0", "key": "57529d8b603137811616c5934d7d620420f115e416c27bb37d19362e2176cf5d", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De deur staat nog open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "80aca2d56325565cb176bb740766cbdf757a6791d7f6f63c524bde3dfd707e5d", "generation_seconds_batch": 17.868345235008746, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.042832136154175, "target_z": 2.250000152467539, "ce": 5.990842819213867, "genuineness": 3.9048471450805664, "identity": 0.7727369070053101, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/57529d8b603137811616c5934d7d620420f115e416c27bb37d19362e2176cf5d.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-0", "key": "57681b818d5b1e8ddc7bf4d0f15420a14afda0ab339f532f6853c8fd0db023b4", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La porte est encore ouverte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "cdaf491f81f47ad69ac921344425aaaff221bb74bd00a77c5056dc9f3cd4aa8d", "generation_seconds_batch": 19.073175708996132, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4768080413341522, "target_z": -0.03906248842880284, "ce": 5.871703147888184, "genuineness": 4.406930446624756, "identity": 0.5659828782081604, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/57681b818d5b1e8ddc7bf4d0f15420a14afda0ab339f532f6853c8fd0db023b4.mp3" }, { "id": "emo_Impatience_and_Irritability-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-1", "key": "57c127dde5f39ffe954192ae544681799ab7d5199e99f5e1f90ff646a9d7b8d0", "bucket": "emo_Impatience_and_Irritability", "phase": "wording", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I found the little box.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "68b8ec6af620ac89d17d9703c54ba9ae5145481c0d67176d9c90d1fb6d2fe02b", "generation_seconds_batch": 15.369086752063595, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0011215806007385254, "target_z": -0.7343749741349711, "ce": 6.3641486167907715, "genuineness": 4.281409740447998, "identity": 0.31139075756073, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/57c127dde5f39ffe954192ae544681799ab7d5199e99f5e1f90ff646a9d7b8d0.mp3" }, { "id": "emo_Impatience_and_Irritability-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-0", "key": "5836dd838363320dfd3a42e047aa6de020a86a3d9ea92d1799c2582f46028f59", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La puerta sigue abierta.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "f87c35139402f1016025751b7836f7d14c8803095b3e4d570e45d8dc64ca5495", "generation_seconds_batch": 20.335624507977627, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.449036121368408, "target_z": 2.8437498720361725, "ce": 5.967014789581299, "genuineness": 4.005263805389404, "identity": 0.37545883655548096, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/5836dd838363320dfd3a42e047aa6de020a86a3d9ea92d1799c2582f46028f59.mp3" }, { "id": "emo_Impatience_and_Irritability-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-1", "key": "585e30c25bcad564ee00b55be3304d41ac53513e27d05d488e93ecca4a39f5c2", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "421eb45541403b700bec4dd356dcbde7d5c45a9c5763e631368a72e5fdbe953e", "generation_seconds_batch": 18.250473196967505, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05456948280334473, "target_z": -0.6562499972773653, "ce": 6.300607204437256, "genuineness": 4.444586753845215, "identity": 0.6040427088737488, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/585e30c25bcad564ee00b55be3304d41ac53513e27d05d488e93ecca4a39f5c2.mp3" }, { "id": "emo_Impatience_and_Irritability-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-1", "key": "58d34c4ab30a90dae22cc7fa2cd5ea3d8e12b86be23a4fd4fcaa04fbd28534ee", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] He encontrado la cajita.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "b0bf0dfc0c4d6234b53ca14810f4b3b4ad56d0f81169a19bdf664de213091efc", "generation_seconds_batch": 17.923133360920474, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3124556839466095, "target_z": -0.27929687721214064, "ce": 5.665193557739258, "genuineness": 4.093128204345703, "identity": 0.6232372522354126, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/58d34c4ab30a90dae22cc7fa2cd5ea3d8e12b86be23a4fd4fcaa04fbd28534ee.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-1", "key": "594f9bc77af2d44621d49c40216a534608db475cffb23a2265c97f0cab525a62", "bucket": "emo_Impatience_and_Irritability", "phase": "wording", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "e47d8dfc2c3a87250833beb5510f22b7e01126d72289a0e01ca3e78b2b35556d", "generation_seconds_batch": 14.224763804930262, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.003793954849243164, "target_z": -0.7304687557855986, "ce": 6.157639026641846, "genuineness": 4.507347106933594, "identity": 0.6898382902145386, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/594f9bc77af2d44621d49c40216a534608db475cffb23a2265c97f0cab525a62.mp3" }, { "id": "emo_Impatience_and_Irritability-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-1", "key": "59aef82f2861f240be7c89da8842d923a2f2b89871bcc90a702c2a7bc446624d", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I found the little box.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "c76652c2f085b90aab51d00f4d87b7895b744a1f4af3fe9c7bfb1b222738e844", "generation_seconds_batch": 19.001721453969367, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.07637792825698853, "target_z": -0.8476562646341611, "ce": 6.324435234069824, "genuineness": 4.457139015197754, "identity": 0.3763347566127777, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/59aef82f2861f240be7c89da8842d923a2f2b89871bcc90a702c2a7bc446624d.mp3" }, { "id": "emo_Impatience_and_Irritability-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-1", "key": "5a17acb6ef29b57eccd25cd4d419815d1c60340a8e9f1a309ced83a12ea0b41c", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "a27a414d915617c86a81123077e2ebd3eca1cf1a341a4062e7b4a94ae9284a83", "generation_seconds_batch": 18.128538768040016, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5021957755088806, "target_z": -0.0019531527368402434, "ce": 6.165581703186035, "genuineness": 4.042920112609863, "identity": 0.34793710708618164, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/5a17acb6ef29b57eccd25cd4d419815d1c60340a8e9f1a309ced83a12ea0b41c.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-1", "key": "5a1a660dc1f73835a55351cb1ac20b8f22680c9d9d5d43b47d0d8e121660fd31", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "07a07246aa1766a30aeda34b0395ee1a3eb2a5758a5d42f8727a0b5096c14202", "generation_seconds_batch": 19.40244674193673, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7560734152793884, "target_z": 0.36914063980432577, "ce": 6.117925643920898, "genuineness": 4.13078498840332, "identity": 0.6314865350723267, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/5a1a660dc1f73835a55351cb1ac20b8f22680c9d9d5d43b47d0d8e121660fd31.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": "5a4096c397de6a6dad62a783dcdf49b425fa1b1c468e8b6f05f2196b34698bb8", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ee267165839afde95100ba8a266b4b09233383bb7ba4824b699b48445d39824b", "generation_seconds_batch": 13.203592056990601, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0593903064727783, "target_z": 0.8124999509925768, "ce": 5.95112943649292, "genuineness": 3.8295347690582275, "identity": 0.6609162092208862, "hypothesis": "Ik schreef het nummer op die envelop. Lees het goed en controleer de laatste twee cijfers. Bel me wanneer je even tijd hebt.", "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_Impatience_and_Irritability/5a4096c397de6a6dad62a783dcdf49b425fa1b1c468e8b6f05f2196b34698bb8.mp3" }, { "id": "emo_Impatience_and_Irritability-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-1", "key": "5a634a7cee0e6982fb21c5cddb5087c33d5a43a38175b73e1fcc40e5f08c6888", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] He encontrado la cajita.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "7e207f9d7a5a3dccf5e1f53fba748930f327303558490650d3b9234e7c0994b0", "generation_seconds_batch": 14.38587571901735, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16146531701087952, "target_z": -0.5, "ce": 6.09409761428833, "genuineness": 4.758388519287109, "identity": 0.49986517429351807, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/5a634a7cee0e6982fb21c5cddb5087c33d5a43a38175b73e1fcc40e5f08c6888.mp3" }, { "id": "emo_Impatience_and_Irritability-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-0", "key": "5ae0318f21673d6f33bd3655a3c5a5ca43bc26ea9b5bbe5f4f7c9cac6e8abc53", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The door is still open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a3ce31af3fc437b57dedf04c4b46b83a05856c769c80f544befa6070b76891ec", "generation_seconds_batch": 18.32233758503571, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10267260670661926, "target_z": -0.5859375006806586, "ce": 6.181467056274414, "genuineness": 3.9801597595214844, "identity": 0.3140702247619629, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/5ae0318f21673d6f33bd3655a3c5a5ca43bc26ea9b5bbe5f4f7c9cac6e8abc53.mp3" }, { "id": "emo_Impatience_and_Irritability-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-1", "key": "5ae2135d44b297e8f8447443aa346e3088ea5d76016be7720e81b1432ae940e9", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I found the little box.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "088e2c8e9ca5ec6ad53714cc63d2c535977fb227cd185141dce40a765b79234a", "generation_seconds_batch": 22.08885065105278, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.116034597158432, "target_z": -0.5664062346851803, "ce": 6.0305562019348145, "genuineness": 3.9676074981689453, "identity": 0.6062153577804565, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/5ae2135d44b297e8f8447443aa346e3088ea5d76016be7720e81b1432ae940e9.mp3" }, { "id": "emo_Impatience_and_Irritability-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-1", "key": "5b46c14ec8293ce2e5363a8214169777066c5e63e88bc3f9569daa64b70c3700", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "3b203434cb144f311debe74718c710f1aca0f1e6fdf95317dc31a447b78df388", "generation_seconds_batch": 23.330887370975688, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.27236974239349365, "target_z": -0.3378906316364219, "ce": 5.274016857147217, "genuineness": 3.735394239425659, "identity": 0.40122655034065247, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/5b46c14ec8293ce2e5363a8214169777066c5e63e88bc3f9569daa64b70c3700.mp3" }, { "id": "emo_Impatience_and_Irritability-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-1", "key": "5b50da67387dc8ac9fbf7fb36527c7ea5490804c51509f99ce968e1e27e7b637", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I found the little box.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "3989e23190f0f65a9ca98048cd8f16f41027f4f7f3b59fae70dab1a322a2e62a", "generation_seconds_batch": 19.942148179979995, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.017155945301055908, "target_z": -0.7109374897901202, "ce": 6.149696350097656, "genuineness": 4.381826400756836, "identity": 0.4677782356739044, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/5b50da67387dc8ac9fbf7fb36527c7ea5490804c51509f99ce968e1e27e7b637.mp3" }, { "id": "emo_Impatience_and_Irritability-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-1", "key": "5bb9d9eeb87950fb915a328ec45299fc6e113c7a42f209dd2f1421076a37d339", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "e80dd9ffed58b3cfc35c6420dd7d0537160aa0f2b63f0318f0b58b744282e831", "generation_seconds_batch": 20.014769666013308, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8124818801879883, "target_z": 3.3749997495176145, "ce": 5.446769714355469, "genuineness": 3.5690791606903076, "identity": 0.5229353904724121, "hypothesis": "Ich hab sie keine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.1875, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/5bb9d9eeb87950fb915a328ec45299fc6e113c7a42f209dd2f1421076a37d339.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-0", "key": "5bedeaa03b45e3a9080ef2dfffac3823744611a2a932ee85672149649b0bb2d1", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De deur staat nog open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "91c938eb2644bc9608e399e362c0d639e43500a6af32533832271a315e7e3b07", "generation_seconds_batch": 19.17704564507585, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8616330623626709, "target_z": 0.5234375279070049, "ce": 5.919358730316162, "genuineness": 4.017816066741943, "identity": 0.6352166533470154, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/5bedeaa03b45e3a9080ef2dfffac3823744611a2a932ee85672149649b0bb2d1.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": "5c45235ccd1880321a815c66dd53b6e6f21e7fcf88aacdb39ee091373d1d9754", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c1177c163458d344cd00ea41defc8978863e7ea6d56601136d74fed36cba3af0", "generation_seconds_batch": 16.957265347009525, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.064211130142212, "target_z": 2.281249899262519, "ce": 6.1020402908325195, "genuineness": 3.7793264389038086, "identity": 0.6339381337165833, "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_Impatience_and_Irritability/5c45235ccd1880321a815c66dd53b6e6f21e7fcf88aacdb39ee091373d1d9754.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-0", "key": "5c512bbded19a267748c2a9e0233fc023da41ea91d11eba4c63386701404c63a", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De deur staat nog open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "7ae63668e973c42ae157caa5f7350ad563cc134ed3a610433917a8f00ea73aa5", "generation_seconds_batch": 17.979044817970134, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.016632080078125, "target_z": 0.750000108905385, "ce": 6.054384231567383, "genuineness": 4.256305694580078, "identity": 0.4563395082950592, "hypothesis": "De deur staat nog open. Ik heb je jas op stolte gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.10526315789473684, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/5c512bbded19a267748c2a9e0233fc023da41ea91d11eba4c63386701404c63a.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-1", "key": "5c8ed9fd91dd260be2e42d7fc4393ceae00387edd4bb6b7b6c79bcd773b494b4", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "7106fa5629ab235c6133d1a0c88862115602a2fdd44fc130726199150ea10f78", "generation_seconds_batch": 19.234690356068313, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3907674551010132, "target_z": 1.296875034032933, "ce": 5.780362129211426, "genuineness": 3.672633647918701, "identity": 0.5301097631454468, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/5c8ed9fd91dd260be2e42d7fc4393ceae00387edd4bb6b7b6c79bcd773b494b4.mp3" }, { "id": "emo_Impatience_and_Irritability-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-1", "key": "5cda90c425b6fd6bc7369973f5054ba5c48670a5ccfc07833db65e666d275650", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] He encontrado la cajita.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "311007ea2a5404162e49656ab2697fe8cdddd1b5412b21e2a1d8d4096913712a", "generation_seconds_batch": 20.67632290790789, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1587929129600525, "target_z": -0.5039062619115264, "ce": 6.213237762451172, "genuineness": 4.846253395080566, "identity": 0.6953052282333374, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/5cda90c425b6fd6bc7369973f5054ba5c48670a5ccfc07833db65e666d275650.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-0", "key": "5d3d0c434506aebefe66bccb2a36480a470effd81bbb388c552d49a3bffe24ca", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De deur staat nog open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "bdfb656ecf6a1a025df8b66994ed1a57ea7393d53bb901a3be371a44092be25c", "generation_seconds_batch": 18.15530011395458, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4762840270996094, "target_z": 1.4218748924559323, "ce": 5.792276382446289, "genuineness": 3.8420867919921875, "identity": 0.5844202041625977, "hypothesis": "De deur 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_Impatience_and_Irritability/5d3d0c434506aebefe66bccb2a36480a470effd81bbb388c552d49a3bffe24ca.mp3" }, { "id": "emo_Impatience_and_Irritability-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-1", "key": "5d44b2b0903534df538883ff76eae88dd3aa1f194ccf6119ecff86e582025f61", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I found the little box.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "8cc32ba3b3cd3055296c93813adf6af167e0ae2096393830c546b6801660eeed", "generation_seconds_batch": 13.170347981038503, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.00646635890007019, "target_z": -0.7265624938740721, "ce": 6.221180438995361, "genuineness": 4.319066047668457, "identity": 0.44193384051322937, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/5d44b2b0903534df538883ff76eae88dd3aa1f194ccf6119ecff86e582025f61.mp3" }, { "id": "emo_Impatience_and_Irritability-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-0", "key": "5dfa79acd5bf4ba8ff500eadee35e1423534313559d4f380f903e4df40875467", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La puerta sigue abierta.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "975153dbf78d26376a6ef2c891b4ce00d9a122b4b93a7291f3193c8041179c6d", "generation_seconds_batch": 18.409430483006872, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0786210298538208, "target_z": -0.621093770760089, "ce": 5.700935363769531, "genuineness": 4.005263805389404, "identity": 0.6218448877334595, "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_Impatience_and_Irritability/5dfa79acd5bf4ba8ff500eadee35e1423534313559d4f380f903e4df40875467.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_Impatience_and_Irritability", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": "6b863bafab702d32b20d35911b748f6998d4d7154f823988a5e70263d94e9bbe", "generation_seconds_batch": 13.28518233099021, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1962064504623413, "target_z": -0.4492187693987717, "ce": 6.109982967376709, "genuineness": 4.281409740447998, "identity": 0.8117461204528809, "hypothesis": "La route tourna gauche après le pont. Continue. Jusqu'à la petite arrière en bois. Je t'attendrai de l'autre côté.", "wer": 0.15, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/5e0af124ad7421917e897f2876d49b25e213a1bc87e01fe43f09b9c255c2a32f.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": "5e4e8a09f4f1b563f1cf31a26174f1d506a8077998570e9764c6ca6d353465e7", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1e9fcee91a734cb8afe2756565f225ca29820414a2a0239130e61f012ab75c5b", "generation_seconds_batch": 14.20422387495637, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5021957755088806, "target_z": -0.0019531527368402434, "ce": 5.637393951416016, "genuineness": 3.6789097785949707, "identity": 0.539240300655365, "hypothesis": "J'ai écrit le numéro sur l'enveloppe, lis-le bien et vérifie les deux derniers chiffres. Appelle-moi qu'en trois-tu a 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_Impatience_and_Irritability/5e4e8a09f4f1b563f1cf31a26174f1d506a8077998570e9764c6ca6d353465e7.mp3" }, { "id": "emo_Impatience_and_Irritability-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-1", "key": "5efc14b893768980be42d8ed2cb147fd8c6acad09e9ac46f0776d8c135d795be", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] He encontrado la cajita.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "347f18910213626eaf037094840e10824b208e965c3ee6acc11f54d586438f7f", "generation_seconds_batch": 13.052403626032174, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20689603686332703, "target_z": -0.43359376531481975, "ce": 5.744620323181152, "genuineness": 4.319066047668457, "identity": 0.45748192071914673, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/5efc14b893768980be42d8ed2cb147fd8c6acad09e9ac46f0776d8c135d795be.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-0", "key": "5f544d91ff628927130043c3c7caac7bc71c5117a1d59c814885bc750742a0c6", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De deur staat nog open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "618d2af3a05abde0b8cf1c002e18f59ee483fbefb8c452839dce52828fd4dd86", "generation_seconds_batch": 18.923114534001797, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.38661468029022217, "target_z": -0.1708984249928972, "ce": 6.09409761428833, "genuineness": 4.268857479095459, "identity": 0.6760725975036621, "hypothesis": "De deur stapt 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_Impatience_and_Irritability/5f544d91ff628927130043c3c7caac7bc71c5117a1d59c814885bc750742a0c6.mp3" }, { "id": "emo_Impatience_and_Irritability-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-1", "key": "5f5f0b1615536635c2273676035e1ccd978686dc350c6659c0b6727545ee9fe3", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] He encontrado la cajita.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "45b41f520790de0a091e3bdc2e4d8393f4868048ab4e8c90f5e35b46e39f4317", "generation_seconds_batch": 18.421126605011523, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.041636765003204346, "target_z": -0.7968749904707788, "ce": 6.181467056274414, "genuineness": 4.68307638168335, "identity": 0.6575713157653809, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/5f5f0b1615536635c2273676035e1ccd978686dc350c6659c0b6727545ee9fe3.mp3" }, { "id": "emo_Impatience_and_Irritability-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-0", "key": "5fe882493d6cfc6b28862de7a37b249f22b3cb6ae527478ebeab4f94d67fe2d5", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The door is still open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "5740073b1c3471c3f2c098b56d757a59af0d3092d59f033e6558e782eefd70dc", "generation_seconds_batch": 18.818258743966, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15344813466072083, "target_z": -0.5117187421724254, "ce": 6.070269584655762, "genuineness": 3.835810661315918, "identity": 0.3492274582386017, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/5fe882493d6cfc6b28862de7a37b249f22b3cb6ae527478ebeab4f94d67fe2d5.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": "5feaef507d1efb4947d0fa75c12031633b78fe3eda4d08527347c8f4811e2deb", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "1e44cc9d7c9ccbaa5849c9c79d19b25fb0b75e84654ba7bc3e385f93b1ee7435", "generation_seconds_batch": 13.343703162972815, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7007653713226318, "target_z": 1.750000021781077, "ce": 5.982900142669678, "genuineness": 3.9173994064331055, "identity": 0.37574484944343567, "hypothesis": "Jemand hat den kleinen blauen Stuhl umgestellt. Er stand hier neben dem hohen Bücherregal. Wir stellen ihn nach dem Essen zurück.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/5feaef507d1efb4947d0fa75c12031633b78fe3eda4d08527347c8f4811e2deb.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": "602898a6b9841c59b700b9a5ef9ff5df77cd66c28240a9086a0cc9868116bf39", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "26add628d3c90ae79462258cbb424d5a59c9ecb03e41080dfd07b7c7128440eb", "generation_seconds_batch": 13.158372025936842, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0000736713409424, "target_z": 2.1874999618831152, "ce": 5.597680568695068, "genuineness": 3.9550557136535645, "identity": 0.43231916427612305, "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_Impatience_and_Irritability/602898a6b9841c59b700b9a5ef9ff5df77cd66c28240a9086a0cc9868116bf39.mp3" }, { "id": "emo_Impatience_and_Irritability-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-1", "key": "6098f35c420ee80a0fa5a064582f81c528a84ab43c2d49720aa1a4745dfa8536", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "b127ca152208db70cfc8bf10f49594f112835eeea93f9455c2d14c1e8950099e", "generation_seconds_batch": 17.96994951996021, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.31913667917251587, "target_z": -0.26953124421440144, "ce": 5.6532793045043945, "genuineness": 3.9425034523010254, "identity": 0.18266810476779938, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/6098f35c420ee80a0fa5a064582f81c528a84ab43c2d49720aa1a4745dfa8536.mp3" }, { "id": "emo_Impatience_and_Irritability-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-1", "key": "613cd2d0d3b6afaa3102d2f2f1356a0a9993e681146a9e3f53af150c59e71e2c", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] He encontrado la cajita.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "8ebcfea54c84b2ba95518a27a59b46a691e24259dea3b701d25a25c86dfa4e95", "generation_seconds_batch": 20.67632290790789, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0011215806007385254, "target_z": -0.7343749741349711, "ce": 6.221180438995361, "genuineness": 4.6956281661987305, "identity": 0.5590689182281494, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/613cd2d0d3b6afaa3102d2f2f1356a0a9993e681146a9e3f53af150c59e71e2c.mp3" }, { "id": "emo_Impatience_and_Irritability-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-1", "key": "61bf63234c74f4310ca4cca214e38f5bbe77944e17b50ee450e109d75e737182", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "96ace45c57e9b077b020136c4a194e9188e1d9938d54b0db9d4d92e7eda41350", "generation_seconds_batch": 14.483517669024877, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05991426110267639, "target_z": -0.6484375170164665, "ce": 6.41180419921875, "genuineness": 4.406930446624756, "identity": 0.6062428951263428, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/61bf63234c74f4310ca4cca214e38f5bbe77944e17b50ee450e109d75e737182.mp3" }, { "id": "emo_Impatience_and_Irritability-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-0", "key": "61c51c55c562baae77674cd5def041f4a61bee778e325230f920715727b54c69", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La puerta sigue abierta.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "9107b6bf487d600ef1f2a8de160021802107629a0c4d6d276da5f6769886d0e8", "generation_seconds_batch": 13.455581575981341, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15344813466072083, "target_z": -0.5117187421724254, "ce": 5.728734970092773, "genuineness": 4.055472373962402, "identity": 0.557142436504364, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/61c51c55c562baae77674cd5def041f4a61bee778e325230f920715727b54c69.mp3" }, { "id": "emo_Impatience_and_Irritability-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-1", "key": "61e96db09860c3940cb5e18dd35216dfe9b02289b481e5dc0a5752a5bf7dbadb", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] He encontrado la cajita.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "a058fe586462c9ef47122ffd1278b7456e119828c96f72555a64d997e0e0441f", "generation_seconds_batch": 19.338468339992687, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2937489151954651, "target_z": -0.306640623468518, "ce": 5.95112943649292, "genuineness": 3.986435890197754, "identity": 0.7825636863708496, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/61e96db09860c3940cb5e18dd35216dfe9b02289b481e5dc0a5752a5bf7dbadb.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": "62bf05e140bdceaa64a0513f2913336e62df4339c02450ae5752a70b8748c776", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "96aed37c3b977573f222e003e35af0a4a2b39dc9b383feaf0047a49bc2e1707f", "generation_seconds_batch": 13.554890324943699, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.320761203765869, "target_z": 2.6562499972773654, "ce": 6.070269584655762, "genuineness": 3.9550557136535645, "identity": 0.4378863573074341, "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_Impatience_and_Irritability/62bf05e140bdceaa64a0513f2913336e62df4339c02450ae5752a70b8748c776.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-1", "key": "62eeafa981674b15e29787f487b6b3dc70a1373eab197442a61f3ecacdaec8cd", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "09a0599cd7f74708205e4651d14cbaa85dba50401c14d7f8861338f07bd58263", "generation_seconds_batch": 18.523337046965025, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6531861424446106, "target_z": 0.21874997005101912, "ce": 5.919358730316162, "genuineness": 4.118232727050781, "identity": 0.5790921449661255, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/62eeafa981674b15e29787f487b6b3dc70a1373eab197442a61f3ecacdaec8cd.mp3" }, { "id": "emo_Impatience_and_Irritability-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-0", "key": "62f59f9aaf577ad114c8d972cec1d74b0a1e87901cebe15aee12bd71f2344787", "bucket": "emo_Impatience_and_Irritability", "phase": "wording", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La puerta sigue abierta.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "f22ebeda0028a23a61c54f6890f7f722cf44549e0ba7c97a8f730f3ecbe1f72a", "generation_seconds_batch": 15.41233797208406, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2576715648174286, "target_z": -0.35937500680658657, "ce": 5.772419452667236, "genuineness": 4.331617832183838, "identity": 0.6241021156311035, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/62f59f9aaf577ad114c8d972cec1d74b0a1e87901cebe15aee12bd71f2344787.mp3" }, { "id": "emo_Impatience_and_Irritability-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-1", "key": "636cc378fc2980b08c091ca058b72c35aaf45d78bd4dec1b755bf8d4d925370f", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I found the little box.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "24d14f28758b97408bffb1c401b8e4e6055d4c1f24d6a1e49c04b8fe4ddea595", "generation_seconds_batch": 17.962664840044454, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16280150413513184, "target_z": -0.4980468908253138, "ce": 6.062326908111572, "genuineness": 4.105680465698242, "identity": 0.6023533344268799, "hypothesis": "I f 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_Impatience_and_Irritability/636cc378fc2980b08c091ca058b72c35aaf45d78bd4dec1b755bf8d4d925370f.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-1", "key": "637912304a92e9b0ffc3c546d0a92acb9f12ebce4ed75d7a653f1167e632fc7f", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0064d21ed33891d18d00587a08aa45e0c61edaec244e86f0a99123faf65bec17", "generation_seconds_batch": 18.733814411098137, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.027845531702041626, "target_z": -0.6953124857061682, "ce": 5.95112943649292, "genuineness": 4.570107460021973, "identity": 0.7782256603240967, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/637912304a92e9b0ffc3c546d0a92acb9f12ebce4ed75d7a653f1167e632fc7f.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-1", "key": "638038ee7f1cdf21351e28dc329199eb5bc7ce96d7cbc721caf0026bf08d0b74", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "59e9c3c1946e7cd0c7dc83d44484231d613b5a0895c71024133567f139540307", "generation_seconds_batch": 19.404811788001098, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.850419521331787, "target_z": 1.968749991832096, "ce": 5.323658466339111, "genuineness": 3.722842216491699, "identity": 0.513593316078186, "hypothesis": "Ik heb een kleine toosje gevonden. Het stond naast het alle ramen. We kunnen er samen in kijken.", "wer": 0.2222222222222222, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/638038ee7f1cdf21351e28dc329199eb5bc7ce96d7cbc721caf0026bf08d0b74.mp3" }, { "id": "emo_Impatience_and_Irritability-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-0", "key": "63c006311974c2557ed5717a31b5ec48c32d6c3976ff62049731fd8f24b49dfb", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The door is still open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "d269c32b809d27976c0373140e58a68bd00f488ba5c3d089a4fcccaa6232b78e", "generation_seconds_batch": 13.959948294912465, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.278002977371216, "target_z": 2.5937501551901736, "ce": 5.696964263916016, "genuineness": 3.550251007080078, "identity": 0.2532023787498474, "hypothesis": "The 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_Impatience_and_Irritability/63c006311974c2557ed5717a31b5ec48c32d6c3976ff62049731fd8f24b49dfb.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-0", "key": "63fa97610971c5d1795c3b069c63a784b720f66274ce70f0d7c43bb4196da7a6", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La porte est encore ouverte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "16b98b909da7e0c21ed126fa9856438481e6bfb853c16d3ed28c2480af392dc5", "generation_seconds_batch": 14.229802518966608, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10534501075744629, "target_z": -0.5820312387691322, "ce": 6.046441555023193, "genuineness": 4.607763767242432, "identity": 0.5066570043563843, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/63fa97610971c5d1795c3b069c63a784b720f66274ce70f0d7c43bb4196da7a6.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-0", "key": "652222ec45046ae1ab1e9b48f53be9cfcc326d1e97d72e86058bc5a51a6f41c4", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La porte est encore ouverte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "1a321e1efa6db6954973c2a2e99ebd41077ec52db8412b821093ba3ba10bdb41", "generation_seconds_batch": 18.409461498027667, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14008614420890808, "target_z": -0.5312500081679039, "ce": 6.24500846862793, "genuineness": 4.545003414154053, "identity": 0.6748507618904114, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/652222ec45046ae1ab1e9b48f53be9cfcc326d1e97d72e86058bc5a51a6f41c4.mp3" }, { "id": "emo_Impatience_and_Irritability-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-1", "key": "657459c79588f32ba957b9065877c391649fcad98b986284e08a7d570c6a2397", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "3e631d70a72939481742a889c4db5298719c9229e55739868d263a0c20018bda", "generation_seconds_batch": 18.851149516995065, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014483541250228882, "target_z": -0.7148437517016466, "ce": 6.300607204437256, "genuineness": 4.319066047668457, "identity": 0.48441457748413086, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/657459c79588f32ba957b9065877c391649fcad98b986284e08a7d570c6a2397.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": "6617fbf0b89a6d2a3c9404418b498fc1f0128cad743db9b52c8440513084a327", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "435dcaaa2a64b0ff51682bb88bbbffba08d3e5aa67978edc835455f6e541a7a1", "generation_seconds_batch": 13.376433706027456, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.499523401260376, "target_z": -0.0058593710862127266, "ce": 5.8875885009765625, "genuineness": 3.8671910762786865, "identity": 0.5030328035354614, "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_Impatience_and_Irritability/6617fbf0b89a6d2a3c9404418b498fc1f0128cad743db9b52c8440513084a327.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-0", "key": "661d6d3da5da1c40e691d816f4b8e2ed6411ee56419de4b1f327ec7d9b5ad81d", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De deur staat nog open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "9dc347d57d5235232c5f4543e04f32f9c79a21df76eadc599d4af30fcbcd5520", "generation_seconds_batch": 17.884217155049555, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7026255130767822, "target_z": 0.2910156629467201, "ce": 5.990842819213867, "genuineness": 4.344170093536377, "identity": 0.581207275390625, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/661d6d3da5da1c40e691d816f4b8e2ed6411ee56419de4b1f327ec7d9b5ad81d.mp3" }, { "id": "emo_Impatience_and_Irritability-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-1", "key": "66464868d939c51c582af78e71ac46872d7bf73409797a8cd09d1f25cb2dab93", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "d72b54001e1bdb7ba035b3d00860245e21c19151994666e26b7318bd8a40606a", "generation_seconds_batch": 17.568160369992256, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04120749235153198, "target_z": -0.6757812632728438, "ce": 6.3641486167907715, "genuineness": 4.331617832183838, "identity": 0.4779932498931885, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/66464868d939c51c582af78e71ac46872d7bf73409797a8cd09d1f25cb2dab93.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-0", "key": "664dbb1102a2ca5938455920fbe0cfbbd715d8a6ba2cece037cf384afb2651c0", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De deur staat nog open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7fcc6813d63d50c4901a581a1a38da5337fccf025681a7cd7723b21cebab61cf", "generation_seconds_batch": 20.18019890296273, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.453856945037842, "target_z": 4.3124998203061145, "ce": 5.605623245239258, "genuineness": 3.5188708305358887, "identity": 0.4360298216342926, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/664dbb1102a2ca5938455920fbe0cfbbd715d8a6ba2cece037cf384afb2651c0.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-1", "key": "6712954ed58b0f8371d92b707ceb2b200f044dab02900fe32c27cff1391ec1f8", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "0e3c468ad5eb1b711b4449d563919b8c9996eb9075418285facaa2307f72b1fb", "generation_seconds_batch": 17.66570413496811, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.042832136154175, "target_z": 2.250000152467539, "ce": 5.260117053985596, "genuineness": 3.528284788131714, "identity": 0.19171042740345, "hypothesis": "Ik heb een kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/6712954ed58b0f8371d92b707ceb2b200f044dab02900fe32c27cff1391ec1f8.mp3" }, { "id": "emo_Impatience_and_Irritability-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-1", "key": "6719b1069eca5b1d3a04885b20de45973c9a8e62eaa957c7b239e80de17b7eb9", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] He encontrado la cajita.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "daa427fdb16593f8c7db6d8bdb8f288a50deca7afdece1d7c21977d7a2cd9832", "generation_seconds_batch": 13.31577121396549, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1823205947875977, "target_z": 0.992187563301255, "ce": 5.307773113250732, "genuineness": 3.8169827461242676, "identity": 0.6767963767051697, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana. ¡Mi hija! 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_Impatience_and_Irritability/6719b1069eca5b1d3a04885b20de45973c9a8e62eaa957c7b239e80de17b7eb9.mp3" }, { "id": "emo_Impatience_and_Irritability-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-0", "key": "673ae2a025663b1916ca70f03bf6720ac2e0c635b428651148ef5bf8f10d9877", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The door is still open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "2a15cc38316c4ea88da49187582d462333003f7c46d1b7b6e5a1154035c903fd", "generation_seconds_batch": 17.894780700909905, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10000020265579224, "target_z": -0.5898437625921852, "ce": 6.197352409362793, "genuineness": 4.21237325668335, "identity": 0.27510982751846313, "hypothesis": "The 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_Impatience_and_Irritability/673ae2a025663b1916ca70f03bf6720ac2e0c635b428651148ef5bf8f10d9877.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": "67c405752ac902cec1d9bdd6ec7a7fc29c7b356adb26afad40d64a2ed6fe2a56", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "a1250fa53daf658735d43223a0a146c583d14d6d83287867323d135dad2c966c", "generation_seconds_batch": 13.554890324943699, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4762840270996094, "target_z": 1.4218748924559323, "ce": 5.824047088623047, "genuineness": 3.936227321624756, "identity": 0.6759527921676636, "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_Impatience_and_Irritability/67c405752ac902cec1d9bdd6ec7a7fc29c7b356adb26afad40d64a2ed6fe2a56.mp3" }, { "id": "emo_Impatience_and_Irritability-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-1", "key": "67f83531e0f5299c5948820ceae99fa5bdc06ef180baa2e058d5688fbc2fd2bf", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "452da994e85bbb637daccf408ca297a9080e71f33c64c4eff8b8ed5d81a0aaaf", "generation_seconds_batch": 19.87047669501044, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07594865560531616, "target_z": -0.6249999891094615, "ce": 6.141753673553467, "genuineness": 4.105680465698242, "identity": 0.46132126450538635, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/67f83531e0f5299c5948820ceae99fa5bdc06ef180baa2e058d5688fbc2fd2bf.mp3" }, { "id": "emo_Impatience_and_Irritability-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-0", "key": "682adfbe4f81f338acd153463a065574196a623fd95ee0eb0ee024dbd92440c4", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La puerta sigue abierta.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "28bff1cfed32bad5aebb05510673ac3c0bd89481549873a8c93c8fb70178b43f", "generation_seconds_batch": 20.710262104985304, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1320689618587494, "target_z": -0.5429687503403293, "ce": 5.637393951416016, "genuineness": 4.068024158477783, "identity": 0.47691741585731506, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/682adfbe4f81f338acd153463a065574196a623fd95ee0eb0ee024dbd92440c4.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": "68885b915b496184140d5548d8b8de06bd8b455f6c5dee2d01e40776d64e1ef0", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "85842f956b9a1098738f8fbe01e4d33f56fe6d001930ed54286a6857c9d2e96d", "generation_seconds_batch": 13.106147442013025, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.748868465423584, "target_z": 1.8203124748156296, "ce": 5.911416053771973, "genuineness": 4.017816066741943, "identity": 0.7200818061828613, "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_Impatience_and_Irritability/68885b915b496184140d5548d8b8de06bd8b455f6c5dee2d01e40776d64e1ef0.mp3" }, { "id": "emo_Impatience_and_Irritability-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-0", "key": "691cd81d0fd5021d8e017c279d9afa11580efb7a7d97bb78b56df96ef80ebf5d", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La puerta sigue abierta.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "64912778607a41c29b9032ef7c6876b2f39f6d34df31dc6558b672d173b9371f", "generation_seconds_batch": 18.351708677015267, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17215490341186523, "target_z": -0.48437499591604805, "ce": 5.744620323181152, "genuineness": 4.143336772918701, "identity": 0.45529818534851074, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/691cd81d0fd5021d8e017c279d9afa11580efb7a7d97bb78b56df96ef80ebf5d.mp3" }, { "id": "emo_Impatience_and_Irritability-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-0", "key": "69a971830acda030a0fdc2a8eaed919385908ac734378cce3f77fbeb970424cb", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The door is still open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "a7c2872fb037a3338fe9e2f0f1f39fe6c0047666c87850dd50c4723350b0873c", "generation_seconds_batch": 20.940930979908444, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11870697140693665, "target_z": -0.5625000163358077, "ce": 6.324435234069824, "genuineness": 4.118232727050781, "identity": 0.2838055491447449, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/69a971830acda030a0fdc2a8eaed919385908ac734378cce3f77fbeb970424cb.mp3" }, { "id": "emo_Impatience_and_Irritability-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-1", "key": "6a019929e64e6c8a36568f8d4e5720e6c653f1070305555a91c74eed809e1c36", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] He encontrado la cajita.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "69333e3fd85611c4c4ee4384a84eda4356eec069840d40600aa602eef9836e07", "generation_seconds_batch": 17.837154263979755, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23896479606628418, "target_z": -0.38671875306296394, "ce": 4.675338268280029, "genuineness": 3.7416701316833496, "identity": 0.4191347360610962, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/6a019929e64e6c8a36568f8d4e5720e6c653f1070305555a91c74eed809e1c36.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_Impatience_and_Irritability", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": "d21a177320d366b717c9a6a04a92e1c5e3cf7b4fc86b4904589f5fea224ec687", "generation_seconds_batch": 13.723297380958684, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10267260670661926, "target_z": -0.5859375006806586, "ce": 6.292664527893066, "genuineness": 3.8797430992126465, "identity": 0.17654722929000854, "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_Impatience_and_Irritability/6a61bc20d43b3e97640d8dd45682f7055c5dbaa5aa987cdb55f8a7d7a432a2c2.mp3" }, { "id": "emo_Impatience_and_Irritability-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-1", "key": "6a7c25ff67c366db074946a7f5806cbd5b1f28a5e058f078029d99ad4eee4501", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I found the little box.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "9d17251a83d6b05a204d5ebc5a06b332d7c5664447d3cf261e6d233b3081f0f9", "generation_seconds_batch": 18.18818409391679, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.041636765003204346, "target_z": -0.7968749904707788, "ce": 6.308549880981445, "genuineness": 4.457139015197754, "identity": 0.39970260858535767, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/6a7c25ff67c366db074946a7f5806cbd5b1f28a5e058f078029d99ad4eee4501.mp3" }, { "id": "emo_Impatience_and_Irritability-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-0", "key": "6a90daf9a67d4bcdd3a85f21948bb169944ee5aad426d2d88fb0ea8139cebf44", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La puerta sigue abierta.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "4b605ecca08317f5b982b54bcb57883ed2e500a31a4370f006ca6d817a4c35ec", "generation_seconds_batch": 17.98246810596902, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05724188685417175, "target_z": -0.6523437353658389, "ce": 5.9431867599487305, "genuineness": 4.15588903427124, "identity": 0.6415493488311768, "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_Impatience_and_Irritability/6a90daf9a67d4bcdd3a85f21948bb169944ee5aad426d2d88fb0ea8139cebf44.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-1", "key": "6ac5da947df8b762bc9b1b577b3f20cef13d69a90aa6a4cd7fd7847e218216cf", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "4dcea231cf8198ebbd54b67d9e2fd7256637da55ab16d444b0e710d0bdae41e8", "generation_seconds_batch": 18.958957261987962, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19086167216300964, "target_z": -0.4570312496596707, "ce": 6.070269584655762, "genuineness": 4.65797233581543, "identity": 0.7376296520233154, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/6ac5da947df8b762bc9b1b577b3f20cef13d69a90aa6a4cd7fd7847e218216cf.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-0", "key": "6b4aeaf1687d92d5619f223f327a0b0d7b70d1e76a8f637e9caa23130c644424", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La porte est encore ouverte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "ae1ed4e317003a693d0d2d4e3e8efe6a27396c323368a49bd9bde6f30959078e", "generation_seconds_batch": 13.10670509096235, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2777145504951477, "target_z": -0.33007810781336894, "ce": 6.181467056274414, "genuineness": 4.532451152801514, "identity": 0.5383785367012024, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/6b4aeaf1687d92d5619f223f327a0b0d7b70d1e76a8f637e9caa23130c644424.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_Impatience_and_Irritability", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": "9e839be3dba9ac3d809ac278c5744b9a64c1af46838c29169c2605408dc46692", "generation_seconds_batch": 13.553846615948714, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13474136590957642, "target_z": -0.5390624884288029, "ce": 6.173524379730225, "genuineness": 4.68307638168335, "identity": 0.6831086874008179, "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_Impatience_and_Irritability/6b973c750e3616c70f28663c29496a0c74bea4a87dff4bad65cadc5394b99131.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-0", "key": "6b9fe6d6c034561af7d0160e9e3c83ad94bb14e8688d21694d6acb6126933405", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La porte est encore ouverte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "5e9ab4e5fc632b14116f406e9e2c7b86830815ab2ef462396837a4b9e8c1af21", "generation_seconds_batch": 17.955940387910232, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.35120540857315063, "target_z": -0.2226562755246996, "ce": 5.982900142669678, "genuineness": 4.362998008728027, "identity": 0.6738055348396301, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/6b9fe6d6c034561af7d0160e9e3c83ad94bb14e8688d21694d6acb6126933405.mp3" }, { "id": "emo_Impatience_and_Irritability-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-1", "key": "6ba12f1478c7537bfa30f378fab0955df2228a4ab4213ab03bda2da336bb318c", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "3a38c9b7fbb21e5a83f402e47dbc5891641bb60e9b60d4f0a4e91c57ee89c947", "generation_seconds_batch": 19.48980699502863, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08663824200630188, "target_z": -0.6093749850255096, "ce": 6.252951145172119, "genuineness": 4.444586753845215, "identity": 0.4877377152442932, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/6ba12f1478c7537bfa30f378fab0955df2228a4ab4213ab03bda2da336bb318c.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": "6ba987c60e574d96c5ad256ac578123a8cde7694d3611372d445221c98fc04b7", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4a0cea01118419258f38126112ff8ec92336d1d93b6292231ac1a677f3028d62", "generation_seconds_batch": 15.34798226703424, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1609413623809814, "target_z": 0.9609374680090431, "ce": 5.772419452667236, "genuineness": 4.18726921081543, "identity": 0.5769100189208984, "hypothesis": "Mi carretera gira a la izquierda tras el puente. Sigue hasta la pequeña puerta de madera. Te esperaré al otro lado.", "wer": 0.047619047619047616, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/6ba987c60e574d96c5ad256ac578123a8cde7694d3611372d445221c98fc04b7.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": "6bd7ed4d1b77903c88bf2da1148ad62be99f3e0e90a723ae0747f177845a8f5d", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "636c6efae6b07b8d0e6abd5c60dc3c91db983c4944fa60e77c7154f578e70671", "generation_seconds_batch": 13.426427079946734, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.641448736190796, "target_z": 3.1250000326716156, "ce": 5.8875885009765625, "genuineness": 3.6098732948303223, "identity": 0.5737919807434082, "hypothesis": "Quelqu'un a déplacé la petite chaise bleue ! Elle était tige près de la grande bibliothèque. Nous la remettrons après le déjeuner.", "wer": 0.047619047619047616, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/6bd7ed4d1b77903c88bf2da1148ad62be99f3e0e90a723ae0747f177845a8f5d.mp3" }, { "id": "emo_Impatience_and_Irritability-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-1", "key": "6c0aaf873555d2246ebceeef98387c2c1614f24f52d15ad284f803ffab4bb708", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "39d5f4a9b2361f986b91dd4e5b975da2360091361b30615c85ed5d9e803a9aa3", "generation_seconds_batch": 13.284366386011243, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06525906920433044, "target_z": -0.6406249931934135, "ce": 6.467403411865234, "genuineness": 4.595211505889893, "identity": 0.575262725353241, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/6c0aaf873555d2246ebceeef98387c2c1614f24f52d15ad284f803ffab4bb708.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-0", "key": "6c25897b29186c38cf4b72837344b31ccafe35d34672aa32e724c46fc744c8b5", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La porte est encore ouverte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "e7c5c9f937b9ef1dd10d02786e0dbc9252d6d51b8054ddc9016e7b128aaff44c", "generation_seconds_batch": 13.10670509096235, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3952999711036682, "target_z": -0.15820310645205163, "ce": 5.6334228515625, "genuineness": 4.080576419830322, "identity": 0.5855627059936523, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/6c25897b29186c38cf4b72837344b31ccafe35d34672aa32e724c46fc744c8b5.mp3" }, { "id": "emo_Impatience_and_Irritability-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-1", "key": "6c27d27a8b2b694c7dc97ec72ec91fe6cfa2e5753423b804a7436c6f4f68f464", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] He encontrado la cajita.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "9651bf07f4ad20c45b6f363e68f44950060b29546358aa92ffcfe96b3cd90ed9", "generation_seconds_batch": 18.15506736910902, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07060384750366211, "target_z": -0.6328125129325145, "ce": 6.022613525390625, "genuineness": 4.457139015197754, "identity": 0.5800584554672241, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/6c27d27a8b2b694c7dc97ec72ec91fe6cfa2e5753423b804a7436c6f4f68f464.mp3" }, { "id": "emo_Impatience_and_Irritability-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-1", "key": "6c3b609489179ee75c3ccdb289a0123183f4d8691f32ef21c314b3ca37785bfe", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "93677f85da8657dbb4bba408ec721906e840702d35328bc3feab8cf333681834", "generation_seconds_batch": 17.875798788038082, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0973278284072876, "target_z": -0.5937499809415576, "ce": 6.38003396987915, "genuineness": 4.632867813110352, "identity": 0.3201529383659363, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/6c3b609489179ee75c3ccdb289a0123183f4d8691f32ef21c314b3ca37785bfe.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": "6c5610a457dd102088d1db500264bdf868b35c82f62123a3931e0258a4719db1", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "407b161b911f5be66b3d4ab0f21bcb02125094e1e5b2f17463bf480635ca9c5b", "generation_seconds_batch": 21.892505299067125, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.026273727416992, "target_z": 3.687500005445269, "ce": 5.9431867599487305, "genuineness": 3.7667744159698486, "identity": 0.28742122650146484, "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_Impatience_and_Irritability/6c5610a457dd102088d1db500264bdf868b35c82f62123a3931e0258a4719db1.mp3" }, { "id": "emo_Impatience_and_Irritability-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-0", "key": "6c90d577884a785aef88356bc415647288dc4b348332552eb9a260169175ba9a", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Tür ist noch offen.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e2e308ecd0801d077c9a5c5f6c484f9d6a46cec78fa0e9379b066134dc03c5cb", "generation_seconds_batch": 13.083557576988824, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.817302942276001, "target_z": 4.8437500462847884, "ce": 5.593709468841553, "genuineness": 3.6789097785949707, "identity": 0.3379766047000885, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/6c90d577884a785aef88356bc415647288dc4b348332552eb9a260169175ba9a.mp3" }, { "id": "emo_Impatience_and_Irritability-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-1", "key": "6cd4dd3beffff18f76f414085d04b5c9ae1ae8ee01067e7e23bf3e98162ad6c8", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "84554ac71e17747044b4d292716511af3b9b0c7810d87c13235eaabc2d736dc3", "generation_seconds_batch": 18.34267005394213, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.033619582653045654, "target_z": -0.7851562482983534, "ce": 6.340320587158203, "genuineness": 4.419482707977295, "identity": 0.5109078288078308, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/6cd4dd3beffff18f76f414085d04b5c9ae1ae8ee01067e7e23bf3e98162ad6c8.mp3" }, { "id": "emo_Impatience_and_Irritability-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-0", "key": "6d18e514806a7e5946c94a772017a7d9c0e34c2601b87bb237f16609ae886611", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Tür ist noch offen.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "489c3b4e7634f7b407bbe15ffa66bfb60f3026fd9f8fe36ec8bf6ac3622467a9", "generation_seconds_batch": 14.235988761065528, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.33517104387283325, "target_z": -0.2460937598695505, "ce": 6.1020402908325195, "genuineness": 4.482243061065674, "identity": 0.5598176121711731, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/6d18e514806a7e5946c94a772017a7d9c0e34c2601b87bb237f16609ae886611.mp3" }, { "id": "emo_Impatience_and_Irritability-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-1", "key": "6d49a4789548d70c79447135bbfa75473913923125a6a3611196d56028cff45e", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9f9aa95f378dcba75706e01bb859faecff33555d7645515087ddac865c9eeeb8", "generation_seconds_batch": 17.86316180205904, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2683611512184143, "target_z": -0.3437500027226346, "ce": 6.09409761428833, "genuineness": 4.482243061065674, "identity": 0.5193037390708923, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/6d49a4789548d70c79447135bbfa75473913923125a6a3611196d56028cff45e.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": "6d5ff7130bd477f3ac9d5140717a53216de73576075956318c4d140301245fec", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Escribí el número en el sobre.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "49b9bdc49988f2aa6c22b41c48df45951e545641cb594b85327def51d60f0562", "generation_seconds_batch": 13.65558570495341, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8910293579101562, "target_z": 0.5664061911230263, "ce": 6.109982967376709, "genuineness": 3.8420867919921875, "identity": 0.3834879398345947, "hypothesis": "Escribí el número en el sobre. Léelo bien y comprueba las dos últimas cifras. Llámame cuando tengas un momento.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/6d5ff7130bd477f3ac9d5140717a53216de73576075956318c4d140301245fec.mp3" }, { "id": "emo_Impatience_and_Irritability-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-0", "key": "6d9661030b5e7034dc0a4c3cb1a2e4538562b5f52961c3424be94f6f583b7218", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The door is still open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "5d8f03bc3b463a8b41a81bbd761aab3c89ab4f6065abd2c7022b975e70745c10", "generation_seconds_batch": 18.32233758503571, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16681009531021118, "target_z": -0.492187519739101, "ce": 6.125868320465088, "genuineness": 4.055472373962402, "identity": 0.40335220098495483, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/6d9661030b5e7034dc0a4c3cb1a2e4538562b5f52961c3424be94f6f583b7218.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": "6dd8c7d4cfadd31e37ec3fed2d65c9dd7be2a94900bfd66a25244632c106e7bb", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6aae90604e86a1fbd9a7e3e61827cb62a222aaabf94ad8899b7daa5632b7a98d", "generation_seconds_batch": 16.653743503033184, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6312830448150635, "target_z": 1.6484374734543124, "ce": 6.09409761428833, "genuineness": 3.961331605911255, "identity": 0.2618952989578247, "hypothesis": "De sleutels liggen op de keukentafel. Keken de la en daarna naast het raam. Neem ze mee als je weggaat!", "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_Impatience_and_Irritability/6dd8c7d4cfadd31e37ec3fed2d65c9dd7be2a94900bfd66a25244632c106e7bb.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-0", "key": "6def760aed434360f8d20d620963ce4894f6b76bc9948847e7ca5fa2921eb22f", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De deur staat nog open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "b467578cf7bf6a6d1ee6e294f8863042249ea8c5362766edf9df09554c6483b5", "generation_seconds_batch": 13.259298200020567, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8028403520584106, "target_z": 0.43750002722634623, "ce": 6.125868320465088, "genuineness": 4.15588903427124, "identity": 0.7385594844818115, "hypothesis": "De deur 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_Impatience_and_Irritability/6def760aed434360f8d20d620963ce4894f6b76bc9948847e7ca5fa2921eb22f.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-1", "key": "6e19c8b369b336f2b9d077e081db5838c76ba15f45d051d22e1d7d5ccd4170ce", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "83496daa40db6114a2a237fac35761e29b648ec03c5dbbd5c2e412105fefcf2e", "generation_seconds_batch": 13.125145087018609, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.380077838897705, "target_z": 1.281249986386827, "ce": 5.903473377227783, "genuineness": 3.8797430992126465, "identity": 0.32416895031929016, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/6e19c8b369b336f2b9d077e081db5838c76ba15f45d051d22e1d7d5ccd4170ce.mp3" }, { "id": "emo_Impatience_and_Irritability-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-0", "key": "6e225ad3d4af29635b881288d70d1132f2807820065d09be4d5cc5052b349294", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La puerta sigue abierta.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "a41d564514fb13d153573e5d7dbae631fa848cdfc3f2b0cb8bdb57e7adced69a", "generation_seconds_batch": 18.13834633899387, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14008614420890808, "target_z": -0.5312500081679039, "ce": 6.038498878479004, "genuineness": 4.262581825256348, "identity": 0.35208800435066223, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/6e225ad3d4af29635b881288d70d1132f2807820065d09be4d5cc5052b349294.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-0", "key": "6e6f62cafe06b4e0c56c8ea430a06207f4b02e65d747350b1497dc329afa691f", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La porte est encore ouverte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "0b6be2336ba931a2ed0042d1cf173ccbf0ccad5ad8671e777f6d4a532f6054f5", "generation_seconds_batch": 13.143054000101984, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2964212894439697, "target_z": -0.30273440511914557, "ce": 6.086154937744141, "genuineness": 4.532451152801514, "identity": 0.449086457490921, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/6e6f62cafe06b4e0c56c8ea430a06207f4b02e65d747350b1497dc329afa691f.mp3" }, { "id": "emo_Impatience_and_Irritability-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-0", "key": "6e8bbe56feb1cef4f8a52da347113e82a6e0e7c2b54415cfa06c41475a864746", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The door is still open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "ba91f60d13025e892b9cfdefd4bf59e53c0b3db8e44d5d7eacd450d38805f0cd", "generation_seconds_batch": 19.9431867870735, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.499523401260376, "target_z": -0.0058593710862127266, "ce": 6.117925643920898, "genuineness": 3.7667744159698486, "identity": 0.6095251441001892, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/6e8bbe56feb1cef4f8a52da347113e82a6e0e7c2b54415cfa06c41475a864746.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-0", "key": "6e9401976e6d30f25d7c7fb68c53bcfcd8985dfd4f1363170a5666eb0f0c7218", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De deur staat nog open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "45ec21d2fe934f5549a0f754785b062a64e0a88022bcbecfdcf5dd90854188c4", "generation_seconds_batch": 13.21820282691624, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7702476978302002, "target_z": 1.8515625701078415, "ce": 6.086154937744141, "genuineness": 4.111956596374512, "identity": 0.7159756422042847, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/6e9401976e6d30f25d7c7fb68c53bcfcd8985dfd4f1363170a5666eb0f0c7218.mp3" }, { "id": "emo_Impatience_and_Irritability-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-0", "key": "6f1597e78a2b48eb9af8e89d97736d2605408fcdd64ac577b1ff8f8eea273ac2", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Tür ist noch offen.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "cf7668170c8535d5b65789b383db510aa9a92b19a8f8bfdcf953d78c43836962", "generation_seconds_batch": 18.843642206978984, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.31913667917251587, "target_z": -0.26953124421440144, "ce": 6.125868320465088, "genuineness": 4.344170093536377, "identity": 0.38863134384155273, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/6f1597e78a2b48eb9af8e89d97736d2605408fcdd64ac577b1ff8f8eea273ac2.mp3" }, { "id": "emo_Impatience_and_Irritability-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-1", "key": "6fe53b0f7f7ae51ea5451993be61d2ad7e7e39ebd387c348a5790ef0d2932edc", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] He encontrado la cajita.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "a460e66cc4ceaefef9e140e81b1d1d987be9a07cdf70a6d7698671bef34d7eee", "generation_seconds_batch": 20.157502248999663, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7026255130767822, "target_z": 0.2910156629467201, "ce": 5.198561668395996, "genuineness": 3.7165660858154297, "identity": 0.5863685607910156, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/6fe53b0f7f7ae51ea5451993be61d2ad7e7e39ebd387c348a5790ef0d2932edc.mp3" }, { "id": "emo_Impatience_and_Irritability-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-0", "key": "7054ce0c73bc7fa690bf25cb82d06d0998d9f5a900fbd117f5019c4f634f044d", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La puerta sigue abierta.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "b228a7ccffab210cf315f27c1e11a7a2584ae51e18ce7cfeb3d478a46fd03151", "generation_seconds_batch": 18.409430483006872, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13474136590957642, "target_z": -0.5390624884288029, "ce": 5.561938762664795, "genuineness": 4.055472373962402, "identity": 0.6718121767044067, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/7054ce0c73bc7fa690bf25cb82d06d0998d9f5a900fbd117f5019c4f634f044d.mp3" }, { "id": "emo_Impatience_and_Irritability-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-0", "key": "706cd40dc3e54cab7b66ad354310316b1f1aafdb5bf3713779abd9eb149ab4b7", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Tür ist noch offen.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "04c74cc740cae425d47648b03c0a1996d5639ab2f45d0dad02cbd379b4928a84", "generation_seconds_batch": 20.813233845983632, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1011006832122803, "target_z": 3.7968748162221626, "ce": 5.744620323181152, "genuineness": 3.823258876800537, "identity": 0.3667939603328705, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/706cd40dc3e54cab7b66ad354310316b1f1aafdb5bf3713779abd9eb149ab4b7.mp3" }, { "id": "emo_Impatience_and_Irritability-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-0", "key": "70cab0f84ca84d0557e04f3150e7df73641bf5d5fdbd7565e3d3e8bae6479b58", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Tür ist noch offen.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "065ba99f8d60924b1cfd5a18c617fa189e6a232e62edc74e1d150e1789ca1fba", "generation_seconds_batch": 13.109840751974843, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8041765689849854, "target_z": 0.4394531799631865, "ce": 5.895530700683594, "genuineness": 4.375550270080566, "identity": 0.5833480954170227, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/70cab0f84ca84d0557e04f3150e7df73641bf5d5fdbd7565e3d3e8bae6479b58.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": "71213f5cc8ed3ab3654baed77c59d1c077a1bac98b050cdad9bde5a55d1a6b82", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Your message arrived after I had left.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6921af61f054da80d7c8c31baefbe104959a3ae2a2358670ab5580efeffd286d", "generation_seconds_batch": 14.079175698920153, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3907674551010132, "target_z": 1.296875034032933, "ce": 5.478540420532227, "genuineness": 3.528284788131714, "identity": 0.30113518238067627, "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_Impatience_and_Irritability/71213f5cc8ed3ab3654baed77c59d1c077a1bac98b050cdad9bde5a55d1a6b82.mp3" }, { "id": "emo_Impatience_and_Irritability-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-0", "key": "713ea0d387823edfeff063669097948d4369b44403f6714cb4888df1ffc741b1", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La puerta sigue abierta.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "c13c8f2dd417876751b98cb5be89f1f67d886d04eb90ee623ad60843d9ef35de", "generation_seconds_batch": 19.853847934980877, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.017155945301055908, "target_z": -0.7109374897901202, "ce": 5.80021858215332, "genuineness": 4.118232727050781, "identity": 0.6494699716567993, "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_Impatience_and_Irritability/713ea0d387823edfeff063669097948d4369b44403f6714cb4888df1ffc741b1.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": "71d487ee7fb5b44b03a534365409c34f33cd31eb25bd2b23d2437b638b67d331", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Escribí el número en el sobre.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b5b224d9284f850f438662f1470ed47e703545b0ab2c76aa27e2e91e39ddf0b2", "generation_seconds_batch": 15.555460990057327, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3926275670528412, "target_z": -0.1621093683635781, "ce": 6.062326908111572, "genuineness": 4.124508857727051, "identity": 0.5359651446342468, "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_Impatience_and_Irritability/71d487ee7fb5b44b03a534365409c34f33cd31eb25bd2b23d2437b638b67d331.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": "73664d8900f1b868b958b157d361852df872491b0e9acb0df4b66f433b39a856", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b238d80c20fc4831e7b2dd6512e04902968c15ad027100a55c794b12b33ecc96", "generation_seconds_batch": 14.163754429086111, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.19248628616333, "target_z": 2.468750122518558, "ce": 5.748591423034668, "genuineness": 3.6663577556610107, "identity": 0.7109662294387817, "hypothesis": "Je bericht kwam nadat ik vertrokken was. Ik las een fikje en legde mijn telefoon weg. Zeg maar wanneer we kunnen praten?", "wer": 0.13043478260869565, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/73664d8900f1b868b958b157d361852df872491b0e9acb0df4b66f433b39a856.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-0", "key": "736e3cef42f23168727e9282270529903e348344a4c4a0e9b9f1cb28e737578a", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De deur staat nog open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "6174c73adc4e61b51879850a5dca091854bfbec6902a59c6c51cc6761c2f17ac", "generation_seconds_batch": 17.833909997018054, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7373666167259216, "target_z": 0.3417968499857944, "ce": 6.062326908111572, "genuineness": 3.961331605911255, "identity": 0.6926084160804749, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/736e3cef42f23168727e9282270529903e348344a4c4a0e9b9f1cb28e737578a.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-0", "key": "738106b07528b8f38600f81098fde948f2f9ae4998f58499807dd51463d705a2", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La porte est encore ouverte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "f95598fb775f51d54802a454cdf2d9dbd2b83f5d16c391ea67b1e3d22580683f", "generation_seconds_batch": 19.88298625696916, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2496543824672699, "target_z": -0.37109374897901204, "ce": 6.046441555023193, "genuineness": 4.545003414154053, "identity": 0.7356703281402588, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/738106b07528b8f38600f81098fde948f2f9ae4998f58499807dd51463d705a2.mp3" }, { "id": "emo_Impatience_and_Irritability-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-0", "key": "7386f056b403fa2de5c786f25f5bb22ca4d4ac15c5d47f26c22fc13c2cea64c1", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Tür ist noch offen.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "5fe9c3c02b39ca150aa244916dcaf20d0fb98cb7b91802a371a74a163c2d8d40", "generation_seconds_batch": 20.813233845983632, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.240065336227417, "target_z": 3.999999912875692, "ce": 5.831989288330078, "genuineness": 3.8044304847717285, "identity": 0.43864119052886963, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/7386f056b403fa2de5c786f25f5bb22ca4d4ac15c5d47f26c22fc13c2cea64c1.mp3" }, { "id": "emo_Impatience_and_Irritability-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-0", "key": "73bc702fa9a02a968b9ab8d90e951224e36e9f1f6dfc0b717b00054b9677cb3d", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The door is still open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "d5528109f987ffd3854b60dccd50500d8d652f52e0a3f77ec55d1801f8316045", "generation_seconds_batch": 19.679495714022778, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16146531701087952, "target_z": -0.5, "ce": 6.24500846862793, "genuineness": 4.005263805389404, "identity": 0.2985268235206604, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/73bc702fa9a02a968b9ab8d90e951224e36e9f1f6dfc0b717b00054b9677cb3d.mp3" }, { "id": "emo_Impatience_and_Irritability-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-1", "key": "7414507fb07274d755e3b8e78df4ee43276bf62d5bfafc0aaaf8180c07727cee", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I found the little box.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "81b88a3bc719ccde0bad6bd2cde1097b77052c59e77c5fd32b44743baf3a78d1", "generation_seconds_batch": 19.73026531690266, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07327625155448914, "target_z": -0.628906251020988, "ce": 6.165581703186035, "genuineness": 4.20609712600708, "identity": 0.44899773597717285, "hypothesis": "I found the little box. It was beside the ol 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_Impatience_and_Irritability/7414507fb07274d755e3b8e78df4ee43276bf62d5bfafc0aaaf8180c07727cee.mp3" }, { "id": "emo_Impatience_and_Irritability-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-1", "key": "744dff39809307cc7c3985989449b7f2181adbd3394d9d2b1db74525c294aa7b", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] He encontrado la cajita.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "7534e751c16d25e114bdb44c1e7135f7fb7c5501b7c0428495d27e83f55645c6", "generation_seconds_batch": 19.55721421202179, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.017155945301055908, "target_z": -0.7109374897901202, "ce": 6.117925643920898, "genuineness": 4.758388519287109, "identity": 0.7203904390335083, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/744dff39809307cc7c3985989449b7f2181adbd3394d9d2b1db74525c294aa7b.mp3" }, { "id": "emo_Impatience_and_Irritability-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-1", "key": "7491cf2de5c44b6e114c1ecccb276afb626abd0eb933a4a253bb3371077ffcc6", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] He encontrado la cajita.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "617b9643f9ad6b1c660c81cf48e2ed46b7387e2c638e23ac84be6cb63b1c3316", "generation_seconds_batch": 17.981277782004327, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24564579129219055, "target_z": -0.37695312006522474, "ce": 5.9431867599487305, "genuineness": 4.632867813110352, "identity": 0.5267667770385742, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/7491cf2de5c44b6e114c1ecccb276afb626abd0eb933a4a253bb3371077ffcc6.mp3" }, { "id": "emo_Impatience_and_Irritability-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-0", "key": "74a802e3ecead2a8ab9777af9a76c3ab3a76ada3ecadec5e1c015204d5ab1170", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Tür ist noch offen.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "d5ed45566f6fc061508a488e36ccea75dcecd9e7988521509b66c22abe3097ae", "generation_seconds_batch": 17.890652947011404, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0214529037475586, "target_z": 2.218750057175327, "ce": 6.2767791748046875, "genuineness": 4.557555198669434, "identity": 0.6533929109573364, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/74a802e3ecead2a8ab9777af9a76c3ab3a76ada3ecadec5e1c015204d5ab1170.mp3" }, { "id": "emo_Impatience_and_Irritability-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-1", "key": "74e043d3d91f6678d1ba55c1c50f59ec8420733ae057ae58c58d3e3e7a07255b", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "739e900b822dc8c16d8ded593a581d3c4ab2ac32ea83fa694fcc3ebf7b284a2c", "generation_seconds_batch": 14.745203869999386, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14008614420890808, "target_z": -0.5312500081679039, "ce": 6.221180438995361, "genuineness": 4.7332844734191895, "identity": 0.7052867412567139, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/74e043d3d91f6678d1ba55c1c50f59ec8420733ae057ae58c58d3e3e7a07255b.mp3" }, { "id": "emo_Impatience_and_Irritability-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-0", "key": "74f47c5a2f51f549117ea02d6d19462f77477c48c90784c6a0123db1574cff4a", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Tür ist noch offen.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "dc72a28ebeed2580cea62ac5147744b9f3276268183bf162f91d3553500e395b", "generation_seconds_batch": 18.843642206978984, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.35120540857315063, "target_z": -0.2226562755246996, "ce": 6.324435234069824, "genuineness": 4.394378662109375, "identity": 0.5423481464385986, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/74f47c5a2f51f549117ea02d6d19462f77477c48c90784c6a0123db1574cff4a.mp3" }, { "id": "emo_Impatience_and_Irritability-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-1", "key": "74f8a8993e898fc8ba33bd6df2b04d3ce0f7fe01902513ed1891cb072fff5a54", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "b9c6a660bf7789fa270580a6d194e76dfad12fc5f02c9263dc09c4235ae268ee", "generation_seconds_batch": 20.153466693940572, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.038535118103027344, "target_z": -0.6796874816222163, "ce": 6.308549880981445, "genuineness": 4.394378662109375, "identity": 0.4354618489742279, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/74f8a8993e898fc8ba33bd6df2b04d3ce0f7fe01902513ed1891cb072fff5a54.mp3" }, { "id": "emo_Impatience_and_Irritability-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-0", "key": "7535773ca33c0da8e956c53bade33b9baf7147aac8c7dcd1439fe7922b9112ce", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The door is still open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "45ac2674c2d4525eed84667da6975847bc87924bfc9ad5ffb317f13b7f6eeacc", "generation_seconds_batch": 18.818258743966, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10534501075744629, "target_z": -0.5820312387691322, "ce": 6.24500846862793, "genuineness": 4.1998209953308105, "identity": 0.22991541028022766, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/7535773ca33c0da8e956c53bade33b9baf7147aac8c7dcd1439fe7922b9112ce.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": "75eb88a73ed6bb9521323a9a722df05334f133c75eaccda88663d3605cbcc123", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bd90b75d025d6d4bca4d0e9ca3ecc322906adf57c4ad631d33818446c44bb63a", "generation_seconds_batch": 14.18419227108825, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2079966068267822, "target_z": 3.95312494418599, "ce": 5.7247633934021, "genuineness": 3.4121780395507812, "identity": 0.42210811376571655, "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_Impatience_and_Irritability/75eb88a73ed6bb9521323a9a722df05334f133c75eaccda88663d3605cbcc123.mp3" }, { "id": "emo_Impatience_and_Irritability-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-0", "key": "75f94ecf6e641d98be2803fd0345024be97c0cad8f6eb0fd98df695dd73d558d", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The door is still open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "391ef6af912f24675778080de45438e9cdb952a5606e98a287efabfb7822a1a6", "generation_seconds_batch": 17.941049939021468, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7841335535049438, "target_z": 0.41015623740781487, "ce": 5.959072113037109, "genuineness": 3.8044304847717285, "identity": 0.3306383192539215, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/75f94ecf6e641d98be2803fd0345024be97c0cad8f6eb0fd98df695dd73d558d.mp3" }, { "id": "emo_Impatience_and_Irritability-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-1", "key": "769e123f3f899d6070494c8244c95d9b15cf4614a14cc4acf13d2ee740a52939", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7ba385014f758cf59464352cfdaeb66f0b1bf0063e60969a99b10efd06b221f9", "generation_seconds_batch": 20.014769666013308, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7560734152793884, "target_z": 0.36914063980432577, "ce": 6.165581703186035, "genuineness": 4.042920112609863, "identity": 0.46645641326904297, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/769e123f3f899d6070494c8244c95d9b15cf4614a14cc4acf13d2ee740a52939.mp3" }, { "id": "emo_Impatience_and_Irritability-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-1", "key": "76b2cd8697aab2e24c4e56e01c85434be5b9a6680aee73ec5d43de1bff4113a0", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] He encontrado la cajita.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "587ac257c5033d80678c780cdd3f6c455ed4ecd10c7ca4d8309a5aff8392db19", "generation_seconds_batch": 18.01843875797931, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22025802731513977, "target_z": -0.41406249931934136, "ce": 6.054384231567383, "genuineness": 4.770940780639648, "identity": 0.6023275852203369, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/76b2cd8697aab2e24c4e56e01c85434be5b9a6680aee73ec5d43de1bff4113a0.mp3" }, { "id": "emo_Impatience_and_Irritability-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-0", "key": "7707227a52c4e5a84b054947ef782f06d8e2ac8341efd6976e0fb470353f7a28", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Tür ist noch offen.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "8af0746e671f5fa35fa1e82aca3a0534329002196d86919f055aa4c12ebad8d4", "generation_seconds_batch": 17.59608573501464, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5596523284912109, "target_z": 0.08203128233128618, "ce": 6.09409761428833, "genuineness": 4.557555198669434, "identity": 0.5491651892662048, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/7707227a52c4e5a84b054947ef782f06d8e2ac8341efd6976e0fb470353f7a28.mp3" }, { "id": "emo_Impatience_and_Irritability-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-0", "key": "771a52877a977b4ffc8d384dc9a8db7a403663f3bc412734e30bc43c5448c272", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The door is still open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "aaa3e0aa069d75af94c18eb5cd9d64d71456aac16fbf6d84f8ff1252bfe25f60", "generation_seconds_batch": 13.233545263065025, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17081871628761292, "target_z": -0.4863281050907343, "ce": 6.181467056274414, "genuineness": 4.432034492492676, "identity": 0.37492337822914124, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/771a52877a977b4ffc8d384dc9a8db7a403663f3bc412734e30bc43c5448c272.mp3" }, { "id": "emo_Impatience_and_Irritability-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-1", "key": "77682ba3c2cff526bcf3791422167f081b8f3f44f86de8ff5c3b23cbb35ae7da", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] He encontrado la cajita.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "36d19cabb789a5760802607718fa89856e5c70922e358e74bfef9314688ab67c", "generation_seconds_batch": 13.477240241016261, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04387989640235901, "target_z": -0.6718750013613173, "ce": 6.09409761428833, "genuineness": 4.846253395080566, "identity": 0.6959473490715027, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/77682ba3c2cff526bcf3791422167f081b8f3f44f86de8ff5c3b23cbb35ae7da.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": "77858bc02f922cbdda680b8c199681af81d10ccfedbdf70ae1bb754b801f894a", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ca85ad88315ebf61f9273f1f2cdca00ca14f65ad87a94cc8bfb455d4a7173248", "generation_seconds_batch": 13.423151803086512, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8397300243377686, "target_z": 1.9531251184346061, "ce": 5.77639102935791, "genuineness": 3.9801597595214844, "identity": 0.41520071029663086, "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_Impatience_and_Irritability/77858bc02f922cbdda680b8c199681af81d10ccfedbdf70ae1bb754b801f894a.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_Impatience_and_Irritability", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": "d800ae4381be38d090405e200bddc6cf25730937bdddf9b8fa89818c56881e24", "generation_seconds_batch": 13.300566393998452, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14543095231056213, "target_z": -0.5234374843448509, "ce": 6.173524379730225, "genuineness": 4.457139015197754, "identity": 0.6671167016029358, "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_Impatience_and_Irritability/77962898fb95ddc0e92a153772191fe01482e40f98d2245158cb92652e8a93c1.mp3" }, { "id": "emo_Impatience_and_Irritability-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-0", "key": "78aba3edba1467b0eda8974a5af6b5a65b7ed59ba8f6d91e0ff133dc99140223", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Tür ist noch offen.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "1a3b092ea0f0467df03a549ef5ee57d095618dce8b999458601ad45e8fbd877c", "generation_seconds_batch": 19.286862999084406, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0807695388793945, "target_z": 0.8437500462847887, "ce": 6.38003396987915, "genuineness": 4.482243061065674, "identity": 0.4856080710887909, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/78aba3edba1467b0eda8974a5af6b5a65b7ed59ba8f6d91e0ff133dc99140223.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": "78c447f864025cb35fb0493d40d9eccfc9fb99f561d0fd45372f10f231e17338", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Your message arrived after I had left.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "54a1e4eee51d6f333dbaa0d8314d3e14bf0b8d32a1d892284963b2779003e0ba", "generation_seconds_batch": 15.26596322399564, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0749008655548096, "target_z": 2.2968751211572407, "ce": 6.078212261199951, "genuineness": 3.7291181087493896, "identity": 0.43685799837112427, "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_Impatience_and_Irritability/78c447f864025cb35fb0493d40d9eccfc9fb99f561d0fd45372f10f231e17338.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": "78f788cc78f8acc9116abec6101855e882b1ad0339e8361561d5904d5162308e", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "106a87d7d1c0d646c8471c0c3f73da616b5f8c3d54e58ff891789e46b4e2e1fd", "generation_seconds_batch": 19.659422751981765, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.58213210105896, "target_z": 4.500000043562154, "ce": 6.006728172302246, "genuineness": 3.8295347690582275, "identity": 0.7066822052001953, "hypothesis": "Ton message était arrivé après mon départ ! Je l'ai relu, puis j'ai rongé mon téléphone ! Dis-moi qu'on nous pourrons parler !", "wer": 0.14285714285714285, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/78f788cc78f8acc9116abec6101855e882b1ad0339e8361561d5904d5162308e.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_Impatience_and_Irritability", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f18cb40be8816711416f5072970ff4435c7d651cd07ac8b9fe34565f63425297", "generation_seconds_batch": 14.637364013004117, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16146531701087952, "target_z": -0.5, "ce": 6.23706579208374, "genuineness": 4.494794845581055, "identity": 0.6382182836532593, "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_Impatience_and_Irritability/794d3b9296e3c4be7c1e4182a2fa3cf095f7d593990763ce0f19c1f5e499a989.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": "794ff21c1ba80dd53ed9a795df82d5479929585b562e0f67cc75f513aeb97f83", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8645646baeff344adf5aeaf55eb3bcbbdedda0ace204629461db81605d03dd6b", "generation_seconds_batch": 18.731546049006283, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.085590362548828, "target_z": 2.312499994554731, "ce": 5.6334228515625, "genuineness": 3.7291181087493896, "identity": 0.1914200484752655, "hypothesis": "De sleutels liggen op de keukentafel. Ik kijk in de la. 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_Impatience_and_Irritability/794ff21c1ba80dd53ed9a795df82d5479929585b562e0f67cc75f513aeb97f83.mp3" }, { "id": "emo_Impatience_and_Irritability-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-0", "key": "79b042f31be5b65bd543abdd9becc631d0a4a5066d5e8e4400f53b686d371156", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Tür ist noch offen.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "0daaabf1322ac95ab755c1e00f0a84df4b87c215d25509fa4c9f884820b4f108", "generation_seconds_batch": 19.385278019937687, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.791102886199951, "target_z": 3.3437500027226346, "ce": 5.557967185974121, "genuineness": 3.9048471450805664, "identity": 0.2877165973186493, "hypothesis": "Die Tür ist noch offen. Ich habe dein Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/79b042f31be5b65bd543abdd9becc631d0a4a5066d5e8e4400f53b686d371156.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": "7a4322cab3f6ba2128574cd5ad3b505a1b15a0e1819a614a27103758f4ddb1a9", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cea76c7ef407c1d182de27262dde32ae935794cf8df84a75d5dcfe5344930dc4", "generation_seconds_batch": 13.302130249910988, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4121465682983398, "target_z": 1.3281249550765286, "ce": 5.879645347595215, "genuineness": 3.9048471450805664, "identity": 0.6627877950668335, "hypothesis": "Les clés sont sur la table de la cuisine. J'ai regardé dans le tiroir, puis près de la fenêtre. Bran-les quand tu partiras.", "wer": 0.041666666666666664, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/7a4322cab3f6ba2128574cd5ad3b505a1b15a0e1819a614a27103758f4ddb1a9.mp3" }, { "id": "emo_Impatience_and_Irritability-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-0", "key": "7a63262a0e9721d0eded499cc44d5abce092321e71a625954ed568feebd616da", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The door is still open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "a6c3415bff01ff800f1f37db20991b2f99d4d4b06a8b0fde43110c8b7bfc02c8", "generation_seconds_batch": 20.135386054054834, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1320689618587494, "target_z": -0.5429687503403293, "ce": 6.229123115539551, "genuineness": 4.068024158477783, "identity": 0.2323753833770752, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/7a63262a0e9721d0eded499cc44d5abce092321e71a625954ed568feebd616da.mp3" }, { "id": "emo_Impatience_and_Irritability-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-0", "key": "7b300a5570efea7a51af94d70d796ae6a70ecf758f7554e983aca363855c49cd", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Tür ist noch offen.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "a79d4fb651b9ba9ad373eb2bb60f02075768acd1a5544e10675f4acb80d60d3a", "generation_seconds_batch": 17.9353584269993, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.769723653793335, "target_z": 3.3124999074304227, "ce": 5.863759994506836, "genuineness": 4.030367851257324, "identity": 0.35967040061950684, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/7b300a5570efea7a51af94d70d796ae6a70ecf758f7554e983aca363855c49cd.mp3" }, { "id": "emo_Impatience_and_Irritability-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-0", "key": "7b80ecbfb25907bf3cd71e53fbe26fcb3878f99142ac70e23e2bc6e4a767710e", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Tür ist noch offen.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "896a441f4e200b6b8b3f11e9a31091f3eb2de58c6fa7bbf6783ea3f5cd46f7d4", "generation_seconds_batch": 18.390069631976075, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4976632595062256, "target_z": 1.4531249877481442, "ce": 6.221180438995361, "genuineness": 4.494794845581055, "identity": 0.24007605016231537, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/7b80ecbfb25907bf3cd71e53fbe26fcb3878f99142ac70e23e2bc6e4a767710e.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-0", "key": "7b8f2e62f004632a9333231e07cbfb8004db0a3b8b26e65428b5c3033053d077", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De deur staat nog open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "994b37a1f63f6acb2996b7092da9fcccd65992ace558c8f32657687e5088491d", "generation_seconds_batch": 17.979140985989943, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.45142027735710144, "target_z": -0.07617186768291945, "ce": 6.24500846862793, "genuineness": 4.262581825256348, "identity": 0.5772976875305176, "hypothesis": "De deur 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_Impatience_and_Irritability/7b8f2e62f004632a9333231e07cbfb8004db0a3b8b26e65428b5c3033053d077.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": "7bba439b94bc75350f45391418f81b02e594c5275674c4ae82fa867efeff9e33", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The keys are on the kitchen table.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "af5586673774149ca9995bcbd7e722dc02ac82a6778509d1e6fce6822f09b337", "generation_seconds_batch": 18.247817363939248, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9658564925193787, "target_z": 0.6757812632728438, "ce": 6.054384231567383, "genuineness": 3.7165660858154297, "identity": 0.683294951915741, "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_Impatience_and_Irritability/7bba439b94bc75350f45391418f81b02e594c5275674c4ae82fa867efeff9e33.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": "7bcaa55208bbdc09c2c154a04f215a910ece77d50719f401282c726affc12671", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Someone moved the little blue chair.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4a194becce761b6f587d4825cea3ed04046393459bd38320ae415540b65b280e", "generation_seconds_batch": 13.862638226011768, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.30042991042137146, "target_z": -0.2968749904707788, "ce": 6.125868320465088, "genuineness": 3.6914620399475098, "identity": 0.42756861448287964, "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_Impatience_and_Irritability/7bcaa55208bbdc09c2c154a04f215a910ece77d50719f401282c726affc12671.mp3" }, { "id": "emo_Impatience_and_Irritability-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-0", "key": "7c4717c61147911d0f1cdb59f5a9377d2bfa3b6d4f580eb07223470d8aac40d4", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The door is still open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "dd6e6b2fa93fff38abb9f7ef94bbe97e214447d8a5defb607becf21e0d9fac8e", "generation_seconds_batch": 18.230404102010652, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18017208576202393, "target_z": -0.47265625374362263, "ce": 6.372091293334961, "genuineness": 4.15588903427124, "identity": 0.3893996775150299, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/7c4717c61147911d0f1cdb59f5a9377d2bfa3b6d4f580eb07223470d8aac40d4.mp3" }, { "id": "emo_Impatience_and_Irritability-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-0", "key": "7d8b182172de80dc7124e9f0c2275627424f6e7af3ffd479508b4f5a6a086719", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La puerta sigue abierta.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "2aeaac7b542089f84146e365f86c61b3ca8798ba13ee1ecead8fa997957c497d", "generation_seconds_batch": 20.300041173002683, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.769723653793335, "target_z": 3.3124999074304227, "ce": 5.395142555236816, "genuineness": 3.7667744159698486, "identity": 0.6935279369354248, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/7d8b182172de80dc7124e9f0c2275627424f6e7af3ffd479508b4f5a6a086719.mp3" }, { "id": "emo_Impatience_and_Irritability-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-1", "key": "7e110aefaef251b1f7f49f17a4d5af3bd30db7e779cf1252310c3aacdce0e54d", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "76a224996bc166aee701595882db4014dc4d3b356d987df18b87b1347b81f805", "generation_seconds_batch": 18.35392912500538, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1427585482597351, "target_z": -0.5273437462563774, "ce": 6.221180438995361, "genuineness": 4.394378662109375, "identity": 0.45690083503723145, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/7e110aefaef251b1f7f49f17a4d5af3bd30db7e779cf1252310c3aacdce0e54d.mp3" }, { "id": "emo_Impatience_and_Irritability-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-1", "key": "7e36f3c9d0306e8f9e845b464557c267e31c3020ee813baa48ca3d6cbceb65a7", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] He encontrado la cajita.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "1a024e158a0ae719349725ce2dedf14f0897b9ab4c8215b6e6d719b8ffc3cc94", "generation_seconds_batch": 21.43543142999988, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0015508532524108887, "target_z": -0.7382812796086515, "ce": 6.205295085906982, "genuineness": 4.570107460021973, "identity": 0.691449761390686, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/7e36f3c9d0306e8f9e845b464557c267e31c3020ee813baa48ca3d6cbceb65a7.mp3" }, { "id": "emo_Impatience_and_Irritability-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-1", "key": "7e5416d52e076e8b1a63b33d913f24de8704c8fca5ff0f7c9af41f455c7984c0", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I found the little box.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "8d10bb6ca0dc2b1a3145a137da4561a5debad315d6518211ace8ad2c163c0013", "generation_seconds_batch": 18.120794444927014, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4647822380065918, "target_z": -0.05664064524959502, "ce": 5.518253803253174, "genuineness": 3.5471129417419434, "identity": 0.18020029366016388, "hypothesis": "I found the little box. It was beside the old We can look inside, together.", "wer": 0.0625, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/7e5416d52e076e8b1a63b33d913f24de8704c8fca5ff0f7c9af41f455c7984c0.mp3" }, { "id": "emo_Impatience_and_Irritability-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-0", "key": "7e73cf1bcd217de085234cfd2444e4b68080ed5fdb1f05a9e2ce7ef7cecae6a4", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La puerta sigue abierta.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "b9ed03dc945dccb6e292a994a0ce43c878256b8e4444bce4ceed565f5ee29e70", "generation_seconds_batch": 17.98246810596902, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22693902254104614, "target_z": -0.4042968663216021, "ce": 6.078212261199951, "genuineness": 4.231201171875, "identity": 0.688522458076477, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/7e73cf1bcd217de085234cfd2444e4b68080ed5fdb1f05a9e2ce7ef7cecae6a4.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": "7e840b70e369e3b4c903424c31f716976617f2de2b65e6d489ae91db0b787fec", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6b8956e73e12125f29ee5f393c8d29b96234ee87799f23983d5d1164fb27d288", "generation_seconds_batch": 13.376433706027456, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.45943745970726013, "target_z": -0.064453125510494, "ce": 5.847874641418457, "genuineness": 3.9299514293670654, "identity": 0.4129525423049927, "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_Impatience_and_Irritability/7e840b70e369e3b4c903424c31f716976617f2de2b65e6d489ae91db0b787fec.mp3" }, { "id": "emo_Impatience_and_Irritability-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-1", "key": "7e99b153eb6f77b5ae2c1791aeb310424140967811dba5358e485bb3ba8aca69", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I found the little box.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "2d545a1a85f205136b5d325c14977bf86975893fb6ab7efb82ad7c0a5ad461ca", "generation_seconds_batch": 13.087213178048842, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13474136590957642, "target_z": -0.5390624884288029, "ce": 5.919358730316162, "genuineness": 3.9801597595214844, "identity": 0.331403911113739, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/7e99b153eb6f77b5ae2c1791aeb310424140967811dba5358e485bb3ba8aca69.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": "7f3025eeaeb38532c6c75d95d7e48893f87fdcf3f424b0f49459607ce7f9de7d", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The keys are on the kitchen table.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5b42d33d5fd1cf4349b91c80a4f703c5c929eb39de85b80a730e07692ed79212", "generation_seconds_batch": 15.550357042928226, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.30042991042137146, "target_z": -0.2968749904707788, "ce": 6.181467056274414, "genuineness": 3.7165660858154297, "identity": 0.5695915818214417, "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_Impatience_and_Irritability/7f3025eeaeb38532c6c75d95d7e48893f87fdcf3f424b0f49459607ce7f9de7d.mp3" }, { "id": "emo_Impatience_and_Irritability-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-1", "key": "7f3770c6f59c9db892857a5be1c686bca78c07fc2daa2e55f67e1039e46ce010", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "9e32d6d14a667fb777b04ad489498dc09fe11faf8c3874c4b26a02b2ac173983", "generation_seconds_batch": 12.773445812985301, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18150827288627625, "target_z": -0.47070314456893636, "ce": 6.205295085906982, "genuineness": 4.149612903594971, "identity": 0.5273690223693848, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/7f3770c6f59c9db892857a5be1c686bca78c07fc2daa2e55f67e1039e46ce010.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": "7f441a9552ca371f836bfd43248e2f578a639649bce8f4f43f3d442f64ae6bf6", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "81319931878c71895990d9fed44e42c311619aafcc950fadd4681806cb82a6c0", "generation_seconds_batch": 13.16130738100037, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2945611476898193, "target_z": 1.1562499537152113, "ce": 5.081407070159912, "genuineness": 3.735394239425659, "identity": 0.7580597400665283, "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_Impatience_and_Irritability/7f441a9552ca371f836bfd43248e2f578a639649bce8f4f43f3d442f64ae6bf6.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_Impatience_and_Irritability", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": "4635e4d900ef157eff6e2fa57932cd629d57e674e5742a8c1baa89ac67eadd2c", "generation_seconds_batch": 14.892576234065928, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11336219310760498, "target_z": -0.5703124965967067, "ce": 6.372091293334961, "genuineness": 4.356721878051758, "identity": 0.3293249011039734, "hypothesis": "The keys are all on the kitchen table. I checked the drawer, then looked beside the window. Take them with you when you leave.", "wer": 0.043478260869565216, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/7f6fce1a6f733719f45a363f28fee4e24b2f07a3396aa07b42392913d7c24239.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-0", "key": "7ffaad7b740af12127e54246274880fcfca108f05c790e341bf91d181664e84f", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De deur staat nog open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "dbbe64d7e3920fe05188742f5e9e404f09b9e8ab3acfe2bf24b6888dd215ca54", "generation_seconds_batch": 14.112069704104215, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2624924182891846, "target_z": 1.1093749850255095, "ce": 5.621508598327637, "genuineness": 3.986435890197754, "identity": 0.30547744035720825, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/7ffaad7b740af12127e54246274880fcfca108f05c790e341bf91d181664e84f.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-0", "key": "800ff1408fcab043150d89bc87e18cac4aab0b158ee76f6a0ebf2ece63d97f21", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De deur staat nog open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "423acd0038cd359844918970596b010051c273177bda55193bf487041ead505a", "generation_seconds_batch": 17.833909997018054, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5155577659606934, "target_z": 0.01757811325863818, "ce": 6.1020402908325195, "genuineness": 4.419482707977295, "identity": 0.39196521043777466, "hypothesis": "De deur 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_Impatience_and_Irritability/800ff1408fcab043150d89bc87e18cac4aab0b158ee76f6a0ebf2ece63d97f21.mp3" }, { "id": "emo_Impatience_and_Irritability-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-1", "key": "803f16d4d474bd3a9c1a3389b7ed1bcbf5c3b3d20f7dcd89538ee6062c9426f2", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "c17adfb84e8a2852de925725c632f01e0ced413f2309676f78a12e80e2508127", "generation_seconds_batch": 14.78973232395947, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12939655780792236, "target_z": -0.5468750122518559, "ce": 6.054384231567383, "genuineness": 4.331617832183838, "identity": 0.6100720763206482, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/803f16d4d474bd3a9c1a3389b7ed1bcbf5c3b3d20f7dcd89538ee6062c9426f2.mp3" }, { "id": "emo_Impatience_and_Irritability-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-0", "key": "805b599e2a35b6d8227fdbb247286be0515f1d81e13d615caaafaecd46e32a40", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The door is still open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "f9837ff28866e6accc577b68438792a8c0ab95dd05c6011baa04f908c8a15167", "generation_seconds_batch": 20.135386054054834, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12137937545776367, "target_z": -0.5585937544242813, "ce": 6.1894097328186035, "genuineness": 3.998987913131714, "identity": 0.27877265214920044, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/805b599e2a35b6d8227fdbb247286be0515f1d81e13d615caaafaecd46e32a40.mp3" }, { "id": "emo_Impatience_and_Irritability-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-0", "key": "80a61224164f332584d2b67b4eb7b74c64da5bd740ddae4edc8af59b9bef3999", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Tür ist noch offen.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "9ee8ef366865edf8175a9dad70f89b1bd02958b3df7a73af96e63a0d2cde5383", "generation_seconds_batch": 13.083557576988824, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.5179944038391113, "target_z": 4.406249757685519, "ce": 5.839932441711426, "genuineness": 3.8169827461242676, "identity": 0.47787901759147644, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/80a61224164f332584d2b67b4eb7b74c64da5bd740ddae4edc8af59b9bef3999.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_Impatience_and_Irritability", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": "af99f436e672925e45b1a726b48469464f8af5844fbe035e6a26f96a51a5688d", "generation_seconds_batch": 13.732400184962898, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12137937545776367, "target_z": -0.5585937544242813, "ce": 6.372091293334961, "genuineness": 4.532451152801514, "identity": 0.7078614234924316, "hypothesis": "Las llaves están en la mesa de la cocina. Miren el cajón y luego junto a la ventana. Llévatelas cuando te vayas.", "wer": 0.08695652173913043, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/80c2597a6b8f43b5338a6b37d654868d679f46ded48514b42837ab18fba327ad.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-1", "key": "80d44b80f152c2ffd412dac58f07e83679f7b548b40e26b120cc280206d08739", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "bbdaca50cb16cfecfede29c49090dd2c066b39628a108b04fc766fdced4570d6", "generation_seconds_batch": 21.54308373806998, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18952548503875732, "target_z": -0.4589843588343569, "ce": 5.9431867599487305, "genuineness": 4.532451152801514, "identity": 0.7415157556533813, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/80d44b80f152c2ffd412dac58f07e83679f7b548b40e26b120cc280206d08739.mp3" }, { "id": "emo_Impatience_and_Irritability-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-0", "key": "81579ccd69c8218896b07f8b976e88005a3b8bdcf3e366a3b5a482838bb9f966", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The door is still open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "7e90d5952ca77142d97a7c02aaed296a3bff3ced48117d513da97a70bc4b7831", "generation_seconds_batch": 13.666600982891396, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9899080395698547, "target_z": 0.7109374897901202, "ce": 6.117925643920898, "genuineness": 3.8671910762786865, "identity": 0.2665519118309021, "hypothesis": "The 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_Impatience_and_Irritability/81579ccd69c8218896b07f8b976e88005a3b8bdcf3e366a3b5a482838bb9f966.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-0", "key": "81875ebf33f3a50c021fa0f089f88992c937633dfac61d02baa669df9b40d544", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De deur staat nog open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "9be48c63385ba3b220c7adc89ab90d14aefc7049060ae4f52dc1f7de84387232", "generation_seconds_batch": 17.979044817970134, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.976546049118042, "target_z": 0.6914062237946418, "ce": 5.959072113037109, "genuineness": 4.15588903427124, "identity": 0.33203211426734924, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/81875ebf33f3a50c021fa0f089f88992c937633dfac61d02baa669df9b40d544.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": "832eff6e4b9314ab29b8f8750782fc14fa413752f1981c873e95ffab765e5869", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ae4db047c0bb21db4e07ef5c3f318394b84e5f54574d5ff488888b7413395547", "generation_seconds_batch": 14.18419227108825, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2566237449645996, "target_z": 2.5625000598979617, "ce": 5.530168056488037, "genuineness": 3.5816311836242676, "identity": 0.4137085974216461, "hypothesis": "De sleutels liggen op de keukentafel. Ik klik in de la en daarna, naast het raam, neem ze mee als je weggaat.", "wer": 0.045454545454545456, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/832eff6e4b9314ab29b8f8750782fc14fa413752f1981c873e95ffab765e5869.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-0", "key": "833b6963434665cefec443c2ab8ca12dbd17f26defe5070e77d1ca0f506ad9e1", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La porte est encore ouverte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "2f2ffd1779493fb4cb76c1157cd6982f28bab4e3013527d9b6b7c6261bd76441", "generation_seconds_batch": 18.412709088996053, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.28840410709381104, "target_z": -0.314453147291571, "ce": 6.109982967376709, "genuineness": 4.369274139404297, "identity": 0.6982255578041077, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi. Quand tu es prêt ?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/833b6963434665cefec443c2ab8ca12dbd17f26defe5070e77d1ca0f506ad9e1.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-1", "key": "84087495d8874716b903d11b2e565a9c2fb1dacc9bad37358a16de1796952210", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "f0f6f89b3f43c31f6de2f2b4256fb768411a0d2987eb3c692ceb2cac399861d0", "generation_seconds_batch": 17.903178279986605, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7373666167259216, "target_z": 0.3417968499857944, "ce": 5.569881439208984, "genuineness": 3.8797430992126465, "identity": 0.27937790751457214, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/84087495d8874716b903d11b2e565a9c2fb1dacc9bad37358a16de1796952210.mp3" }, { "id": "emo_Impatience_and_Irritability-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-1", "key": "84b0c4c6c6833993c0c17f81c707ab0ad8929a12008cdb6b8d690c56510d4949", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] He encontrado la cajita.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "58f29292bd2affc6bda2cfc4c6725bba8d5224f9bc3443da8c4fd4c407c5c3de", "generation_seconds_batch": 14.192206317093223, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1507757306098938, "target_z": -0.515625004083952, "ce": 5.804190158843994, "genuineness": 4.482243061065674, "identity": 0.7595797777175903, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/84b0c4c6c6833993c0c17f81c707ab0ad8929a12008cdb6b8d690c56510d4949.mp3" }, { "id": "emo_Impatience_and_Irritability-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-0", "key": "850f7dabe0f05d2a7b3dc00ae2018de33d86d27a4bb2970838a8f508dc8e1819", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The door is still open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "b04ff1f323033fbb83a736a4961ab555ba2c17f187bf2c64e34e8890d43bdee8", "generation_seconds_batch": 19.9431867870735, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5618007183074951, "target_z": 1.5468749251275478, "ce": 5.911416053771973, "genuineness": 3.550251007080078, "identity": 0.42222046852111816, "hypothesis": "The 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_Impatience_and_Irritability/850f7dabe0f05d2a7b3dc00ae2018de33d86d27a4bb2970838a8f508dc8e1819.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": "86107551efc05bff71a4be40142bd2f4d9a490a2f107dd575e29d20eae3f7832", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e6989639ea6c50e7b7d057a72bf1e068ca5dd60c6f0925af9c5c9111496a0c8a", "generation_seconds_batch": 16.957265347009525, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0380111932754517, "target_z": 0.7812500299489809, "ce": 6.1020402908325195, "genuineness": 3.9173994064331055, "identity": 0.4455665647983551, "hypothesis": "Die bericht kwam nadat ik vertrokken was. Ik las het twee keer en legde mijn telefoon weg. Zeg maar, wanneer we kunnen praten.", "wer": 0.043478260869565216, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/86107551efc05bff71a4be40142bd2f4d9a490a2f107dd575e29d20eae3f7832.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": "8641193a12d535d51bf6ec792a1dbf3cd8f056fd159512ff3be9d6fc3a126c7e", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ae97bd6071312dcc213b5b18daf91f84dbf9885ae263ea646a5f12dff1249f5b", "generation_seconds_batch": 13.238258647965267, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.668696641921997, "target_z": 1.7031250530913753, "ce": 5.7128496170043945, "genuineness": 3.722842216491699, "identity": 0.4708332419395447, "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_Impatience_and_Irritability/8641193a12d535d51bf6ec792a1dbf3cd8f056fd159512ff3be9d6fc3a126c7e.mp3" }, { "id": "emo_Impatience_and_Irritability-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-1", "key": "8643bf3ef0439477bf8d3750be20b5e1afa0dbf6c9f28d91420897e1ee7c6043", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "e28e4fd371e58e100dd63a9fb339b909186a43201005d7568f5cfa7c99dac4b4", "generation_seconds_batch": 17.96994951996021, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3298262655735016, "target_z": -0.2539062401304495, "ce": 5.847874641418457, "genuineness": 3.9550557136535645, "identity": 0.3322140574455261, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/8643bf3ef0439477bf8d3750be20b5e1afa0dbf6c9f28d91420897e1ee7c6043.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-1", "key": "866c19f5eae4a687ea7a7641122700e95991b6153429f3ced212fe5237a1328a", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "96162a99099609301f1fa897b6521701eb720c9a676534c63ae99dfe5ab5120f", "generation_seconds_batch": 17.973528189002536, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.011811137199401855, "target_z": -0.7187500136131731, "ce": 6.117925643920898, "genuineness": 4.425758361816406, "identity": 0.5851055383682251, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/866c19f5eae4a687ea7a7641122700e95991b6153429f3ced212fe5237a1328a.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-0", "key": "870a689ac6cc1cf671ad813b4c8374843c419890cad823a787f0609f5a4d117c", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La porte est encore ouverte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "13ae693dad5096fc4504f0ef75068ee5885f86f6cf573a9a0e99ddcf894e7439", "generation_seconds_batch": 13.465286222985014, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5917210578918457, "target_z": 0.128906251020988, "ce": 5.780362129211426, "genuineness": 4.394378662109375, "identity": 0.663661777973175, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/870a689ac6cc1cf671ad813b4c8374843c419890cad823a787f0609f5a4d117c.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-1", "key": "8714259f0e4b81ec87ad3f097f89d5e80c5adc479bf9e6dc436a5d996241b2e3", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a3f748cbeeae71517aaa38cc3241787735d6b88e9a7bbaa420206be787463d02", "generation_seconds_batch": 19.82584500091616, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2149132490158081, "target_z": -0.42187497958024034, "ce": 6.038498878479004, "genuineness": 4.457139015197754, "identity": 0.6691246032714844, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/8714259f0e4b81ec87ad3f097f89d5e80c5adc479bf9e6dc436a5d996241b2e3.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-1", "key": "87cbbfbcb671e0ad9f40e4d2165f6e43165309ebd1103b9a83b7732f81116daa", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": 127, "seconds_generated": 10.16, "mp3_sha256": "15e3304b33200c1c101a9596725cf1d97c823a1eb3cf67c50629c2bab34e5a63", "generation_seconds_batch": 14.050848859013058, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23629239201545715, "target_z": -0.3906250149744904, "ce": 6.1894097328186035, "genuineness": 4.482243061065674, "identity": 0.6034098267555237, "hypothesis": "J'ai trouvé la 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_Impatience_and_Irritability/87cbbfbcb671e0ad9f40e4d2165f6e43165309ebd1103b9a83b7732f81116daa.mp3" }, { "id": "emo_Impatience_and_Irritability-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-0", "key": "87fe3681fc74953d6982de3ad8d2068c4a244d0ee03c59582d6ec0f86f6d3eba", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The door is still open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "847c541a499bf53cbc34c28b66f9c686e34efb127aaaa47835112aea43a96d4d", "generation_seconds_batch": 18.539189837989397, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6257941126823425, "target_z": 0.17871094881595015, "ce": 6.213237762451172, "genuineness": 3.9550557136535645, "identity": 0.40403449535369873, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/87fe3681fc74953d6982de3ad8d2068c4a244d0ee03c59582d6ec0f86f6d3eba.mp3" }, { "id": "emo_Impatience_and_Irritability-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-1", "key": "8828a62c365f3cd3db3dc486f3da30efdf97d9499406cfca00c49cefdcf78684", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I found the little box.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "3f498db21e61d70684625056440615eb9d97a1874b4bca49789296c580b72798", "generation_seconds_batch": 18.712557755061425, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.030947208404541016, "target_z": -0.7812500299489809, "ce": 6.268836498260498, "genuineness": 4.2374773025512695, "identity": 0.2654782235622406, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/8828a62c365f3cd3db3dc486f3da30efdf97d9499406cfca00c49cefdcf78684.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": "884f4ccf39fd7c876bc4bae9c70357cfa18533a04c39cc734166c99e13409895", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d17a0ce6e1579f543e0f15d52dcdeb717c1b2c18c7a9043c9fe2f93a1cf207a6", "generation_seconds_batch": 13.262265203986317, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.3042027950286865, "target_z": 4.0937498502550955, "ce": 5.796247482299805, "genuineness": 3.6789097785949707, "identity": 0.3563460111618042, "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_Impatience_and_Irritability/884f4ccf39fd7c876bc4bae9c70357cfa18533a04c39cc734166c99e13409895.mp3" }, { "id": "emo_Impatience_and_Irritability-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-1", "key": "887cbc72c4d2e5e079ef640930ee823bf487f954665e8ea61c209aaa25ac0725", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I found the little box.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "98c76b308e8e553882e51e09019a75342946bf7ef1f0912322eb46dc59406826", "generation_seconds_batch": 19.697817581007257, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17482730746269226, "target_z": -0.48046873400452156, "ce": 6.284721851348877, "genuineness": 4.381826400756836, "identity": 0.20970270037651062, "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_Impatience_and_Irritability/887cbc72c4d2e5e079ef640930ee823bf487f954665e8ea61c209aaa25ac0725.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-1", "key": "888aafde41831768d5c900e765056a248b2a4b26d2ffb54df5261e549a6f1b68", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "effcc4644088c8dc3413d1d4a16ece46ae66d1620a3117a00588b1c94aacf76b", "generation_seconds_batch": 18.344065628014505, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08663824200630188, "target_z": -0.6093749850255096, "ce": 6.09409761428833, "genuineness": 4.519899368286133, "identity": 0.5178874731063843, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/888aafde41831768d5c900e765056a248b2a4b26d2ffb54df5261e549a6f1b68.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-1", "key": "88b3a8c94e40bad508bb90a2e26b0a09ca64b7266eff817c6c4e844b1e97a7b0", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "a1d4c21cd841c8f1ed28fbf09798043e5fb99e8ca1c236ca4fe8b915479e71f0", "generation_seconds_batch": 13.34224573103711, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6364836692810059, "target_z": 0.1943359093377481, "ce": 6.054384231567383, "genuineness": 4.105680465698242, "identity": 0.6022435426712036, "hypothesis": "Ik heb een klein doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "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_Impatience_and_Irritability/88b3a8c94e40bad508bb90a2e26b0a09ca64b7266eff817c6c4e844b1e97a7b0.mp3" }, { "id": "emo_Impatience_and_Irritability-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-1", "key": "88c304d13e142c35aa91417e7e83e7c0e70168ec1bb0ae3c68ddb9dbeacbfdef", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "d33878e25e5685ad9b960c2f11fe5c2e7de1dc27b13b6b32630d62443c4d680a", "generation_seconds_batch": 17.731988276005723, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1507757306098938, "target_z": -0.515625004083952, "ce": 6.332377910614014, "genuineness": 4.300237655639648, "identity": 0.6858221292495728, "hypothesis": "Ich habe die kleine Schachtel gefunden, sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/88c304d13e142c35aa91417e7e83e7c0e70168ec1bb0ae3c68ddb9dbeacbfdef.mp3" }, { "id": "emo_Impatience_and_Irritability-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-1", "key": "8924ff180a5bb80ffba7918b8fa504a641ef83f2efefb8e0d08990e0a545cedd", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "9579ef2f392004fc16b01f71843286a35a3d598d4e4df01e4955458d043feac6", "generation_seconds_batch": 17.86316180205904, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17482730746269226, "target_z": -0.48046873400452156, "ce": 5.669164657592773, "genuineness": 4.168440818786621, "identity": 0.3681698441505432, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/8924ff180a5bb80ffba7918b8fa504a641ef83f2efefb8e0d08990e0a545cedd.mp3" }, { "id": "emo_Impatience_and_Irritability-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-0", "key": "89acfaf5a6f4601ee09c38fe84e21ea0e5290dc06ac2800769a965ae63470a87", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The door is still open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "6d29b30fdf205778f7381199010bdc787c6ae3aebafefbb743d40514466d0f63", "generation_seconds_batch": 18.230404102010652, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1868530809879303, "target_z": -0.4628906207458834, "ce": 6.149696350097656, "genuineness": 4.068024158477783, "identity": 0.4113369584083557, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/89acfaf5a6f4601ee09c38fe84e21ea0e5290dc06ac2800769a965ae63470a87.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-1", "key": "8a869597e502b9c71dbec8438b81630c713010f68ef1d082a7d5c730aa2156ae", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2a2b461ded0abb6b1427deb1677f8a87f2e5d7dcf285a331296faf6bb681d689", "generation_seconds_batch": 18.09051540098153, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0807695388793945, "target_z": 0.8437500462847887, "ce": 6.0305562019348145, "genuineness": 4.068024158477783, "identity": 0.6909337043762207, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/8a869597e502b9c71dbec8438b81630c713010f68ef1d082a7d5c730aa2156ae.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-1", "key": "8aa36b1ec6a7c01702211501638cff8cbf6186b0c7d6bbfd23e858aadb87f7f4", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "b37bb68e1bea9aee7ac7f06cd83af039e3b33142a083c74f635acc42b1201e92", "generation_seconds_batch": 19.68378479394596, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3244814872741699, "target_z": -0.26171872039134847, "ce": 6.173524379730225, "genuineness": 4.519899368286133, "identity": 0.32164257764816284, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/8aa36b1ec6a7c01702211501638cff8cbf6186b0c7d6bbfd23e858aadb87f7f4.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": "8b396fc18278dfdc4434626010a56bf4c2f8d377ed1dc783c2be7bc3f02c3d4e", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The road turns left behind the bridge.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d796657fc5773adaa205a604a3e16d18bc99b12692b3173bb1eefc6ad50ef948", "generation_seconds_batch": 13.837683302932419, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.722144603729248, "target_z": 1.7812501170732888, "ce": 5.990842819213867, "genuineness": 3.722842216491699, "identity": 0.22457540035247803, "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_Impatience_and_Irritability/8b396fc18278dfdc4434626010a56bf4c2f8d377ed1dc783c2be7bc3f02c3d4e.mp3" }, { "id": "emo_Impatience_and_Irritability-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-0", "key": "8b3d08c3a6995638600328ac31de66fa5eb91eaca2ea941044efb8369491cb82", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La puerta sigue abierta.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "d9393a0ba866031857febf4dcd6ef3844db3ca0de11374d55aad54bda53d7713", "generation_seconds_batch": 14.064703266019933, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0000736713409424, "target_z": 2.1874999618831152, "ce": 5.474569320678711, "genuineness": 3.5816311836242676, "identity": 0.6660251021385193, "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_Impatience_and_Irritability/8b3d08c3a6995638600328ac31de66fa5eb91eaca2ea941044efb8369491cb82.mp3" }, { "id": "emo_Impatience_and_Irritability-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-1", "key": "8b4ebf6a6fb73dda65a266f66008e33d1ce268c2690713d336fa15c426b82595", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I found the little box.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "998db8049aa6c2f6d519e325cd48c3d62e7042f3d644913386c8afbde0eff76d", "generation_seconds_batch": 18.974736292962916, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.009138762950897217, "target_z": -0.7226562319625456, "ce": 6.046441555023193, "genuineness": 4.168440818786621, "identity": 0.38367214798927307, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/8b4ebf6a6fb73dda65a266f66008e33d1ce268c2690713d336fa15c426b82595.mp3" }, { "id": "emo_Impatience_and_Irritability-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-1", "key": "8c1e79d531f02ad7f111072ea8a5e5163e3b29f6a86cf0d10a43c9e6ef385660", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I found the little box.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2f45b8421200e0aaabcd7574333700edca56fb8bd13cd004e00c7c53905172d6", "generation_seconds_batch": 17.882239539991133, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.07637792825698853, "target_z": -0.8476562646341611, "ce": 6.300607204437256, "genuineness": 4.519899368286133, "identity": 0.4463994801044464, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/8c1e79d531f02ad7f111072ea8a5e5163e3b29f6a86cf0d10a43c9e6ef385660.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-0", "key": "8c8d7ab67d68b6dfc12690fb4f8928f43fd71e11f47e03e42ca1fc7a6bc9172e", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La porte est encore ouverte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "c15a755f1c68bdbea7ee5d3f73b28ad76df3f05f323ae66dd836217ab589a840", "generation_seconds_batch": 19.195472339051776, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21624943614006042, "target_z": -0.41992187040555407, "ce": 6.284721851348877, "genuineness": 4.65797233581543, "identity": 0.6128692626953125, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/8c8d7ab67d68b6dfc12690fb4f8928f43fd71e11f47e03e42ca1fc7a6bc9172e.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-1", "key": "8cc6104986161199739a7a8667e5b93f8ecfe5d1173e90c7a8e9b5a9fc2fd953", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "90d33d68602353627ac328ccea628754065f0b30ee0284474ea79420f95f0575", "generation_seconds_batch": 18.147168789990246, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08663824200630188, "target_z": -0.6093749850255096, "ce": 6.125868320465088, "genuineness": 4.595211505889893, "identity": 0.6303256750106812, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/8cc6104986161199739a7a8667e5b93f8ecfe5d1173e90c7a8e9b5a9fc2fd953.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-0", "key": "8d98cc1808268446ad174ee6783acdb4fc76f17743c31d82e0e1112ea051b6ce", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La porte est encore ouverte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "eaa8ccd36f26343e023ce4f8edb2feeb0e9990ce6415f407474797da6ff01102", "generation_seconds_batch": 17.995810942957178, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.116034597158432, "target_z": -0.5664062346851803, "ce": 5.998785495758057, "genuineness": 4.68307638168335, "identity": 0.5189672708511353, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/8d98cc1808268446ad174ee6783acdb4fc76f17743c31d82e0e1112ea051b6ce.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-1", "key": "8e0d5c4bad7988ef62379c9a2fd0adb8855f1b943c43ade0bbb9d84a0b487b14", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9d00b3c2927a678ec702fb337bff72547c6249269b9dfcaaed165c68097f1c0b", "generation_seconds_batch": 19.029261486022733, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21892184019088745, "target_z": -0.4160156084940276, "ce": 5.919358730316162, "genuineness": 4.218649387359619, "identity": 0.7181668877601624, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/8e0d5c4bad7988ef62379c9a2fd0adb8855f1b943c43ade0bbb9d84a0b487b14.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": "8e14d8c2e6cf32433f11db3c65d99f0e1adbe6cac83537c95e0f9365a954ed13", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "a4d0a06ac7951ed7ba411053448a5e9c7040dad12f447d893b453b292089f502", "generation_seconds_batch": 13.016488951048814, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.3042027950286865, "target_z": 4.0937498502550955, "ce": 5.824047088623047, "genuineness": 3.7040140628814697, "identity": 0.5234763026237488, "hypothesis": "¡Ay, quién ha movido la pequeña silla azul! Estaba aquí, junto a la estantería alta. La colocaremos después de comer.", "wer": 0.10526315789473684, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/8e14d8c2e6cf32433f11db3c65d99f0e1adbe6cac83537c95e0f9365a954ed13.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-0", "key": "8e5b7b1edb3da1474581d8c310670803cab1ecb416d77ea5ebcce59d7bc3f0f5", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De deur staat nog open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "5b60691fe1733b9006e4bb6441f02615ee70c872860cb8e7bbdd357692f0726d", "generation_seconds_batch": 19.584259098977782, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.427657127380371, "target_z": 2.812500125241193, "ce": 5.274016857147217, "genuineness": 3.7793264389038086, "identity": 0.2918580174446106, "hypothesis": "De deur staat nog open. Ik heb je jas om 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_Impatience_and_Irritability/8e5b7b1edb3da1474581d8c310670803cab1ecb416d77ea5ebcce59d7bc3f0f5.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": "8e60b42ff7c4be074e512cf6f5d5b63df697f2208b4f4e30df06b673b6bb4750", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "c72946c508269078770b7c8b5dcdfe90fcaa76f143e381a1eb90da65a9e8b1b8", "generation_seconds_batch": 13.16130738100037, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0273215770721436, "target_z": 0.7656249823028749, "ce": 5.458683967590332, "genuineness": 3.9550557136535645, "identity": 0.3883281350135803, "hypothesis": "La carretera qui irá a la izquierda tras el puente. Sigue hasta la pequeña puerta de madera. Te esperaré al otro lado.", "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_Impatience_and_Irritability/8e60b42ff7c4be074e512cf6f5d5b63df697f2208b4f4e30df06b673b6bb4750.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-1", "key": "8e63eb7ededc001b43bf02985857f26ad0b9ddfa3fd06b5b8391bb6ba02f16c0", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "210d457b89204eb85ba7431f2bb42270fa470cf23ea73549085fdf8047d2823f", "generation_seconds_batch": 14.050848859013058, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3779293894767761, "target_z": -0.18359374353374278, "ce": 5.736677646636963, "genuineness": 4.362998008728027, "identity": 0.5719195604324341, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/8e63eb7ededc001b43bf02985857f26ad0b9ddfa3fd06b5b8391bb6ba02f16c0.mp3" }, { "id": "emo_Impatience_and_Irritability-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-0", "key": "8f2a188527b5c2448dbee30adbe415cdc9c2ea567b928b1ca30a5fef00638f39", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La puerta sigue abierta.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "1ae9479ce76c84299852e687542c972b674e2447bf7a961c70fe1d52a33c37a7", "generation_seconds_batch": 18.351708677015267, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12672418355941772, "target_z": -0.5507812306012283, "ce": 5.780362129211426, "genuineness": 4.18099308013916, "identity": 0.5274702906608582, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/8f2a188527b5c2448dbee30adbe415cdc9c2ea567b928b1ca30a5fef00638f39.mp3" }, { "id": "emo_Impatience_and_Irritability-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-0", "key": "8f4d42a01704b9bb98e3ac6c0134abb81c231798871c4af7e479dfe07c4cc3b8", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La puerta sigue abierta.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3e5836b30f292a84b47bfa9da71221ec4b9f0b80f6658186090a783afa0d00fe", "generation_seconds_batch": 13.074674005038105, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1283485889434814, "target_z": 2.3749998366419227, "ce": 6.149696350097656, "genuineness": 3.9173994064331055, "identity": 0.5039235949516296, "hypothesis": "¡La puerta sigue abierta! He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/8f4d42a01704b9bb98e3ac6c0134abb81c231798871c4af7e479dfe07c4cc3b8.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": "8f62b8a3e9edf78ff082875049c79a1dff06920d99677f5b60d9723047bcf42b", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The road turns left behind the bridge.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "15466c499a29dd9913d4f4c20e51c911deb5e5b2b2dee7da0665edb997742e2b", "generation_seconds_batch": 14.331522535998374, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3693883419036865, "target_z": 1.265625112989337, "ce": 5.855817794799805, "genuineness": 3.4372823238372803, "identity": 0.14866766333580017, "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_Impatience_and_Irritability/8f62b8a3e9edf78ff082875049c79a1dff06920d99677f5b60d9723047bcf42b.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": "8f87066b32a53ac7c2f17bc931bcf4994e58128fe8c17b382fb607619a9f6002", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "f9e42da3886e0a642badf0274443565cd87511edf3b79dfdf0b49d2e6b100540", "generation_seconds_batch": 13.106147442013025, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.19248628616333, "target_z": 2.468750122518558, "ce": 5.80021858215332, "genuineness": 3.9927117824554443, "identity": 0.6494691371917725, "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_Impatience_and_Irritability/8f87066b32a53ac7c2f17bc931bcf4994e58128fe8c17b382fb607619a9f6002.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-1", "key": "8fe1580f61c7c382521bf08d93f9baa6bca1a71496ae512a531b9494cd6e6aca", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "a4faa52b4d857d88b68c121a7e3160ec42b9c57fa2bc9c8fbbb6f9ed0fb3aaa1", "generation_seconds_batch": 17.705651398049667, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.33650726079940796, "target_z": -0.24414060713271027, "ce": 6.078212261199951, "genuineness": 4.093128204345703, "identity": 0.3477398753166199, "hypothesis": "Ik 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_Impatience_and_Irritability/8fe1580f61c7c382521bf08d93f9baa6bca1a71496ae512a531b9494cd6e6aca.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": "913e28476f908addae98208717a061137e5cba80398449982f890707cf3ea809", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "0eee94ea0121845d062148a35b46ccba4eb69b4771989c0ccfc78fb684ab7644", "generation_seconds_batch": 15.34798226703424, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8664538860321045, "target_z": 1.9921874761769471, "ce": 5.796247482299805, "genuineness": 3.9676074981689453, "identity": 0.44661659002304077, "hypothesis": "Una carretera iré a la izquierda tras el puente. Sigue hasta la pequeña puerta de madera. Te esperaré al otro lado.", "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_Impatience_and_Irritability/913e28476f908addae98208717a061137e5cba80398449982f890707cf3ea809.mp3" }, { "id": "emo_Impatience_and_Irritability-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-1", "key": "91b317c604717bed52fd5757af9751e7684d7b034a6ead3ee83cbb746893c743", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "c23843d54ee8b379348ea7c31e8732a4214275e2c9dba3a23a9988ae0a668f44", "generation_seconds_batch": 17.994874013005756, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11870697140693665, "target_z": -0.5625000163358077, "ce": 6.268836498260498, "genuineness": 4.3881025314331055, "identity": 0.3133770227432251, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/91b317c604717bed52fd5757af9751e7684d7b034a6ead3ee83cbb746893c743.mp3" }, { "id": "emo_Impatience_and_Irritability-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-1", "key": "91f231455a40087114df95a3d3a64e3f4ead2763dba96c83f39736b56be77cfe", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I found the little box.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "55af6ba10ab104caca2b53d8ba83fdfdce592a878cc2ef920011e8f81e7f8047", "generation_seconds_batch": 20.13860369194299, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22560280561447144, "target_z": -0.4062500190584424, "ce": 5.871703147888184, "genuineness": 3.7416701316833496, "identity": 0.5942513942718506, "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_Impatience_and_Irritability/91f231455a40087114df95a3d3a64e3f4ead2763dba96c83f39736b56be77cfe.mp3" }, { "id": "emo_Impatience_and_Irritability-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-1", "key": "92393ced06b7052a4f6f04455d23034d63e1420b962a9052111134f3540c91ff", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] He encontrado la cajita.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "61c60694d45fb2a6ab3d7f253c593aa4347d1f3515e6722d546dcf743eebc812", "generation_seconds_batch": 18.338985887006857, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.116034597158432, "target_z": -0.5664062346851803, "ce": 6.046441555023193, "genuineness": 4.7834930419921875, "identity": 0.6388446092605591, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/92393ced06b7052a4f6f04455d23034d63e1420b962a9052111134f3540c91ff.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-0", "key": "924b210c35c6cb942ed534ccb5b5a4b9f0d9002a12b2ef561c50414d5eda6dca", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La porte est encore ouverte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "505e62f5ad89de0c6526537180d995557d7969239b61c81d4c2b79af2916e413", "generation_seconds_batch": 18.415875100996345, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.427657127380371, "target_z": 2.812500125241193, "ce": 5.879645347595215, "genuineness": 4.231201171875, "identity": 0.5984163284301758, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/924b210c35c6cb942ed534ccb5b5a4b9f0d9002a12b2ef561c50414d5eda6dca.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-1", "key": "92cdd554c4850308baa12154660e510221834e81d7821b43c7ede98ca929d842", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0e2c5c1afd9e1a9523824b4482aabc2f0164ef1f6b2066ab4725747385b77f7f", "generation_seconds_batch": 13.125145087018609, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.746720016002655, "target_z": 0.3554687448950601, "ce": 5.661221981048584, "genuineness": 4.143336772918701, "identity": 0.5584409832954407, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/92cdd554c4850308baa12154660e510221834e81d7821b43c7ede98ca929d842.mp3" }, { "id": "emo_Impatience_and_Irritability-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-0", "key": "936c5bfe4f9079aaa1e0566ccfc4d525432e931cf9ce47697a40b9e5c7660ad6", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Tür ist noch offen.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "6960b28a5f418a22526cbb637246221ebad40b6c4e2c8db220bd3eafe47d0505", "generation_seconds_batch": 19.041031430009753, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.7745444774627686, "target_z": 4.781249855700365, "ce": 5.847874641418457, "genuineness": 3.4341442584991455, "identity": 0.5906962156295776, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/936c5bfe4f9079aaa1e0566ccfc4d525432e931cf9ce47697a40b9e5c7660ad6.mp3" }, { "id": "emo_Impatience_and_Irritability-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-1", "key": "9375e813a03b703af350e1e039b562b7dec32be3c93dc4a33e088f6c1b3cf79c", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I found the little box.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "a6eddcf75a7399b2f2d09c3c57c118a84469c0eebb51622ff9becdef06ae3c68", "generation_seconds_batch": 18.02963152900338, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.09241229295730591, "target_z": -0.871093748979012, "ce": 6.372091293334961, "genuineness": 4.362998008728027, "identity": 0.44038206338882446, "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_Impatience_and_Irritability/9375e813a03b703af350e1e039b562b7dec32be3c93dc4a33e088f6c1b3cf79c.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-1", "key": "947006fb5950d431ab4d37b8f108b6b94c6751210c997b4cbbb1061874567cbe", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "d39dee2dda1c7adce928eb81452be6de86c7da44edf05271b88ad672bdbb2adc", "generation_seconds_batch": 18.180310201947577, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5222387909889221, "target_z": 0.027343789818531392, "ce": 6.117925643920898, "genuineness": 4.331617832183838, "identity": 0.6145477890968323, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/947006fb5950d431ab4d37b8f108b6b94c6751210c997b4cbbb1061874567cbe.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": "94ffd4bf7a2ac326ccf4f430ab6402f713ff762418ad387675d4a169b1276bde", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "762cb6c1e5c985debd553ead99750a7cd4658b873022cd2d8411203900cd25cb", "generation_seconds_batch": 15.429349728976376, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1681463122367859, "target_z": -0.4902343670022608, "ce": 6.165581703186035, "genuineness": 4.457139015197754, "identity": 0.8059901595115662, "hypothesis": "Les clés sont sur la table de la cuisine. J'ai regardé dans le tiroir, puis près de la fenêtre. Prends-les quand tu partiras.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/94ffd4bf7a2ac326ccf4f430ab6402f713ff762418ad387675d4a169b1276bde.mp3" }, { "id": "emo_Impatience_and_Irritability-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-1", "key": "9513d9793a2477b609fe2030f74f2e7efc660946c9d53f9d999e1eb74cb12b88", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "860939401f3712abe1f6c217e45173ffda19905f1325d961163ce5404c4c9858", "generation_seconds_batch": 14.745203869999386, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.038535118103027344, "target_z": -0.6796874816222163, "ce": 6.260893821716309, "genuineness": 4.432034492492676, "identity": 0.5534137487411499, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/9513d9793a2477b609fe2030f74f2e7efc660946c9d53f9d999e1eb74cb12b88.mp3" }, { "id": "emo_Impatience_and_Irritability-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-1", "key": "953f06326239fc20c5fc5407b6420ec51504ea3ff8c30c3409885cb08f0ecf3d", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] He encontrado la cajita.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "1ccb95fce6e3158914fe6a709424167e48336e37e1e4a16f38155a0be9b7d8d3", "generation_seconds_batch": 20.558270503999665, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07060384750366211, "target_z": -0.6328125129325145, "ce": 6.117925643920898, "genuineness": 4.720732688903809, "identity": 0.8033863306045532, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/953f06326239fc20c5fc5407b6420ec51504ea3ff8c30c3409885cb08f0ecf3d.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-1", "key": "95920215a5831668f1c42ece6df4aa59ce7321b0217a80138f1f527f8ff7a1ed", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fbda718c378cfc51660620c7e76e89242843788d9d70a68e7f6e484c72666394", "generation_seconds_batch": 19.338804801926017, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.2828235626220703, "target_z": 4.062499754962884, "ce": 5.242246150970459, "genuineness": 3.487490653991699, "identity": 0.5132894515991211, "hypothesis": "J'ai trouvé ma 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_Impatience_and_Irritability/95920215a5831668f1c42ece6df4aa59ce7321b0217a80138f1f527f8ff7a1ed.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": "96559b863b14c65e7ccdda370ad866cfb2711eb12bbb72156909d74e1b6f77bd", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "451be6fde61467535521e80462c5fbb61a1d6c6897f99dd06c3bab91d4c46ce7", "generation_seconds_batch": 18.35052423097659, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.829040288925171, "target_z": 1.9374998965398842, "ce": 5.478540420532227, "genuineness": 3.6789097785949707, "identity": 0.1754453480243683, "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_Impatience_and_Irritability/96559b863b14c65e7ccdda370ad866cfb2711eb12bbb72156909d74e1b6f77bd.mp3" }, { "id": "emo_Impatience_and_Irritability-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-1", "key": "965d5f1d031bc6d423cbdb542b951213021b7a51441c22c60a7d0fd58c80a8a3", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "40a4b609ab7bc883b4e5766d1d352d9227d2e68952efef3088b943fac35e324d", "generation_seconds_batch": 14.78973232395947, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17215490341186523, "target_z": -0.48437499591604805, "ce": 6.046441555023193, "genuineness": 4.256305694580078, "identity": 0.5545378923416138, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/965d5f1d031bc6d423cbdb542b951213021b7a51441c22c60a7d0fd58c80a8a3.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-0", "key": "96d41d2876bf477b88c9a2c375759433599cdaf8f009a288e02bfc942a1f4d83", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La porte est encore ouverte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "bc093ce7a62e98ce4cc4181a4b393870ae3d137e5b96ca5ccf272887b08bb351", "generation_seconds_batch": 19.65718134609051, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.26568877696990967, "target_z": -0.3476562210720071, "ce": 5.8875885009765625, "genuineness": 4.281409740447998, "identity": 0.7352843880653381, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/96d41d2876bf477b88c9a2c375759433599cdaf8f009a288e02bfc942a1f4d83.mp3" }, { "id": "emo_Impatience_and_Irritability-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-0", "key": "9715a1786722a04cd0fd2f4e0026e678b871a5b759704d1089013941309f1b14", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La puerta sigue abierta.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "b0309c772d821b84986a7b587576dedb07fc2b28c1e334a5a52cfa406287604b", "generation_seconds_batch": 18.041341340984218, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18818926811218262, "target_z": -0.46093751157119717, "ce": 5.871703147888184, "genuineness": 4.118232727050781, "identity": 0.6203312277793884, "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_Impatience_and_Irritability/9715a1786722a04cd0fd2f4e0026e678b871a5b759704d1089013941309f1b14.mp3" }, { "id": "emo_Impatience_and_Irritability-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-1", "key": "9739bbb489731e83c9744fa7772051bd6457555e7525a937bc65d5a3d41fccb6", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I found the little box.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "85d25b4ac298294f6351ab20222743e34fcd9703c5f3d88489d5b5a6a914fa03", "generation_seconds_batch": 18.332297736080363, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.00646635890007019, "target_z": -0.7265624938740721, "ce": 6.252951145172119, "genuineness": 4.369274139404297, "identity": 0.4777051508426666, "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_Impatience_and_Irritability/9739bbb489731e83c9744fa7772051bd6457555e7525a937bc65d5a3d41fccb6.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-1", "key": "9741b7dd2e51f50d99b5203cd85b8d90871220e3ddbaa1d7144141f17ef7c356", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "aa48c56b0884340b269f94ed3e5674fba1b8e25c1f5c920e2e85590bea777064", "generation_seconds_batch": 19.834195206989534, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.47012704610824585, "target_z": -0.048828121426542054, "ce": 5.728734970092773, "genuineness": 3.9425034523010254, "identity": 0.5986557602882385, "hypothesis": "J' 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_Impatience_and_Irritability/9741b7dd2e51f50d99b5203cd85b8d90871220e3ddbaa1d7144141f17ef7c356.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-1", "key": "979622f2407ec93e24613656331bf9a87d7727c1b29a6708d4314bc46b0ce4f7", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "22baece390737441271226476992102ede859a950269e9d5d1df7478909389d7", "generation_seconds_batch": 14.075085149961524, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4704153537750244, "target_z": 2.8749999673283844, "ce": 5.168776512145996, "genuineness": 3.600459337234497, "identity": 0.2976566553115845, "hypothesis": "Ik 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_Impatience_and_Irritability/979622f2407ec93e24613656331bf9a87d7727c1b29a6708d4314bc46b0ce4f7.mp3" }, { "id": "emo_Impatience_and_Irritability-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-0", "key": "97a29e2918ffe23e3c94f78430ef096612be97a553b64f30b47977a7fec88453", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The door is still open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "c88c3e66a933f74a582ae08f9605a78b1a76ad69d9b281e3c0cc9384955f69a9", "generation_seconds_batch": 18.224620430963114, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.534552812576294, "target_z": 2.968749904707788, "ce": 5.788304805755615, "genuineness": 3.478076457977295, "identity": 0.4872143864631653, "hypothesis": "door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/97a29e2918ffe23e3c94f78430ef096612be97a553b64f30b47977a7fec88453.mp3" }, { "id": "emo_Impatience_and_Irritability-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-0", "key": "97a821adf340ae77b901883267807dfbfa0a593392c227b12cab1f3abc1d9cc0", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The door is still open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "9f2b1ff9e468fbe165461284044721f04d67e79f40564e31fdd8c6eee15382b5", "generation_seconds_batch": 19.293493896955624, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1240517795085907, "target_z": -0.5546874925127547, "ce": 6.1894097328186035, "genuineness": 4.068024158477783, "identity": 0.34397873282432556, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/97a821adf340ae77b901883267807dfbfa0a593392c227b12cab1f3abc1d9cc0.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-1", "key": "9835886ba83fb9363537ec92493836995232306322d7b9125a17c5c1ae84d64a", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "838c173cdbc01abb94ae1f67c1dd9cd2fd4316b7bba1dd06f6292eaabf3a5788", "generation_seconds_batch": 18.884481976972893, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3438563346862793, "target_z": -0.23339844132870494, "ce": 6.141753673553467, "genuineness": 4.331617832183838, "identity": 0.5733858346939087, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/9835886ba83fb9363537ec92493836995232306322d7b9125a17c5c1ae84d64a.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-0", "key": "98dc1715b8e16821d1ccbe512431760f28b0a29a198a009c2e060ec89852cc3b", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La porte est encore ouverte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "5bfc843f5dbb678d508f4f490698c9513977c3bccadfacde88cddaf4a39af5c9", "generation_seconds_batch": 20.736241686041467, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17482730746269226, "target_z": -0.48046873400452156, "ce": 6.205295085906982, "genuineness": 4.6203155517578125, "identity": 0.7126976251602173, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/98dc1715b8e16821d1ccbe512431760f28b0a29a198a009c2e060ec89852cc3b.mp3" }, { "id": "emo_Impatience_and_Irritability-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-1", "key": "98e87c3823ec4e78622d809513634ee2f79e80ba6b746d427b7419fcfddc12ce", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9b1131ef34633bcdf48bc6729be9ed54b32535960e01a7c6c099197a248516b6", "generation_seconds_batch": 20.17597936198581, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23629239201545715, "target_z": -0.3906250149744904, "ce": 6.229123115539551, "genuineness": 4.645420074462891, "identity": 0.6138702034950256, "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_Impatience_and_Irritability/98e87c3823ec4e78622d809513634ee2f79e80ba6b746d427b7419fcfddc12ce.mp3" }, { "id": "emo_Impatience_and_Irritability-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-0", "key": "991bc038bd408d0e84765e078058ad866b21314d43fe67707dfea52b5896154a", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Tür ist noch offen.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "36293510df9f3db7646307d08b859b360c2ee4b55d3d0f2e6589e61929ff9c11", "generation_seconds_batch": 13.478433658950962, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.34920114278793335, "target_z": -0.22558591750565196, "ce": 6.157639026641846, "genuineness": 4.432034492492676, "identity": 0.5573538541793823, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/991bc038bd408d0e84765e078058ad866b21314d43fe67707dfea52b5896154a.mp3" }, { "id": "emo_Impatience_and_Irritability-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-0", "key": "99261196c00ed436c6deb9d41e77674f8f6a7ffb4ba35a06f75c718a994c3d63", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Tür ist noch offen.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "ce0322679b604b221364838c5640f9a9e7652f3c63a7f08256155ecedcf5218f", "generation_seconds_batch": 19.4105680140201, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8183507919311523, "target_z": 1.9218750231423942, "ce": 6.2767791748046875, "genuineness": 4.457139015197754, "identity": 0.5014973282814026, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/99261196c00ed436c6deb9d41e77674f8f6a7ffb4ba35a06f75c718a994c3d63.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_Impatience_and_Irritability", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": "696f7129f8e0ff92d14bd9d926c29099884f8e4f51ed3456eed2f9b6523db70d", "generation_seconds_batch": 13.654272214975208, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.038535118103027344, "target_z": -0.6796874816222163, "ce": 6.4515180587768555, "genuineness": 4.7458367347717285, "identity": 0.4115672707557678, "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_Impatience_and_Irritability/99bf1b7d3eed7b885fdae888ab00b4960791c3971d259b46f771306d2801e39b.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-0", "key": "9a55f9e31961b02c2f691589b7d1d5ecaf4e22b2d6b7e7a6d3cb7a789ed8fad7", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La porte est encore ouverte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "8ba214ba1f818bcb76fc104667159306d30aad138f134fe96824a811e965ea76", "generation_seconds_batch": 19.65718134609051, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2937489151954651, "target_z": -0.306640623468518, "ce": 6.260893821716309, "genuineness": 4.632867813110352, "identity": 0.6710776090621948, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi, quand tu es prêt?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/9a55f9e31961b02c2f691589b7d1d5ecaf4e22b2d6b7e7a6d3cb7a789ed8fad7.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": "9a908ad0058f7fd154e6b7cb5e7fa381a16243c4074bcde2a92a323ae18a3a28", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I wrote the number on the envelope.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4a27f5a0db1342ed97d7f6a45bab9163940a5bed93d7fa3ef27caabb6c361954", "generation_seconds_batch": 13.345635640085675, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7269654273986816, "target_z": 3.250000065343231, "ce": 5.796247482299805, "genuineness": 3.4498343467712402, "identity": 0.29273128509521484, "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_Impatience_and_Irritability/9a908ad0058f7fd154e6b7cb5e7fa381a16243c4074bcde2a92a323ae18a3a28.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-0", "key": "9ae4ff6ce1f03d99a10a6d238fed73e6db49ff4b1162162ae4371e68fb0a1998", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De deur staat nog open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "f5cd4c8710e22856d0c0c6b7e8c57e7d522ca711229e9ce792f66e646aabe2f9", "generation_seconds_batch": 19.584259098977782, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3421404361724854, "target_z": 2.6875000925695773, "ce": 5.895530700683594, "genuineness": 3.8420867919921875, "identity": 0.4234820008277893, "hypothesis": "De deur 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_Impatience_and_Irritability/9ae4ff6ce1f03d99a10a6d238fed73e6db49ff4b1162162ae4371e68fb0a1998.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-1", "key": "9b94db926cd513065526e3c6efec06a749b5687b3eca6849d7aceff5138e5bb4", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "2946fe9883c0bb2bc4c323c3d8ef72de29c7c0ae2a83a40238363db4cee3f23c", "generation_seconds_batch": 18.121481977053918, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4655945301055908, "target_z": 1.4062500190584424, "ce": 6.165581703186035, "genuineness": 4.1998209953308105, "identity": 0.2939642369747162, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/9b94db926cd513065526e3c6efec06a749b5687b3eca6849d7aceff5138e5bb4.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-1", "key": "9b9f2feaba0d949a7fd9463ad2cb358dcd9b41e1c860cee4d56a0281bb034b45", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "85cad792832146cd3eb79dbfb8f5ad00e23f9fc97937d2ab681c24c295dd7292", "generation_seconds_batch": 25.826522713992745, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14543095231056213, "target_z": -0.5234374843448509, "ce": 6.252951145172119, "genuineness": 4.545003414154053, "identity": 0.7482289671897888, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/9b9f2feaba0d949a7fd9463ad2cb358dcd9b41e1c860cee4d56a0281bb034b45.mp3" }, { "id": "emo_Impatience_and_Irritability-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-0", "key": "9be23e8267331f69912c84c08274e555a8bba344ab4bd20b7141e5b734f5144b", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Tür ist noch offen.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "935d34eb41eaac647404b263dbe749017a07fe71ac839a88e754c09dab48d8fe", "generation_seconds_batch": 18.083581804996356, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8873090744018555, "target_z": 3.48437490879174, "ce": 6.022613525390625, "genuineness": 4.356721878051758, "identity": 0.3496286869049072, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/9be23e8267331f69912c84c08274e555a8bba344ab4bd20b7141e5b734f5144b.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_Impatience_and_Irritability", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": "38cab2465ce56efcc8ed90f18285bec314ad53786659b5111ee98e6144f3ce3f", "generation_seconds_batch": 14.188138357014395, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4634460508823395, "target_z": -0.05859375442428127, "ce": 6.292664527893066, "genuineness": 4.375550270080566, "identity": 0.7329516410827637, "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_Impatience_and_Irritability/9c09e940c5dab53287ffae2d1a8fa5296f41b2df71714656aaa2bb8830bf5162.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": "9c1ab7f590dacbad278b86e6f15632c40e34f28f43d4f53c8a07cc20d9125326", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "11f0f8de88c3d608f3b6013a41671aad13c8aef97b81cfeb5f831e14d5ba1d1e", "generation_seconds_batch": 13.17327401903458, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.3897194862365723, "target_z": 4.218749882926711, "ce": 5.839932441711426, "genuineness": 3.9173994064331055, "identity": 0.47114819288253784, "hypothesis": "Deine Nachricht kam, als ich schon weg war. Ich lasse sie zweimal. Dann legte ich das Handy weg. Sag mir, wann wir reden können.", "wer": 0.041666666666666664, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/9c1ab7f590dacbad278b86e6f15632c40e34f28f43d4f53c8a07cc20d9125326.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": "9c2725a6dc4d4d80c81ee9f34768bad5e7c326190f5ee392e78d984354dd0c89", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "713f5a3c704320d5f4a780a3c721b64f8cfb753a2a97ce6ef0f4eb04221e131f", "generation_seconds_batch": 18.631250304053538, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0059423446655273, "target_z": 0.734374887010663, "ce": 5.538110733032227, "genuineness": 3.7040140628814697, "identity": 0.6551050543785095, "hypothesis": "Ik schreef het nummer op de envelop. Is het goed? En controleer de laatste twee cijfers. Bel me wanneer je even tijd hebt.", "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_Impatience_and_Irritability/9c2725a6dc4d4d80c81ee9f34768bad5e7c326190f5ee392e78d984354dd0c89.mp3" }, { "id": "emo_Impatience_and_Irritability-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-1", "key": "9c6b7d7bc3e9e5217b752f3181d01b92f7023e5c898a5f480117a138e04b3190", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "8ec011390613a3c1b115905cd741d7834ac66731c202f37a46d41a2c9399bf73", "generation_seconds_batch": 19.87047669501044, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07327625155448914, "target_z": -0.628906251020988, "ce": 6.221180438995361, "genuineness": 4.293961524963379, "identity": 0.5469140410423279, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/9c6b7d7bc3e9e5217b752f3181d01b92f7023e5c898a5f480117a138e04b3190.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_Impatience_and_Irritability", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": "993034e55bfe41a358552cc0e0b9f7e2b5255a02f8c28ffbc2737ae8d11a95d2", "generation_seconds_batch": 13.826158610987477, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22025802731513977, "target_z": -0.41406249931934136, "ce": 6.078212261199951, "genuineness": 4.582659721374512, "identity": 0.7488574981689453, "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_Impatience_and_Irritability/9c969db20a6db380e08592f6aed9c9189b3db634d677ebe8f573f593ebdfd2d3.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-0", "key": "9ca1560b87b2b9449783ccf1fbffe852bd514f934e29114c2066ae055ada6ac4", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La porte est encore ouverte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "a1660230a4149a4e47eaefc535e6726eba2eb484fa32b54bfaf411157a27fca6", "generation_seconds_batch": 18.409461498027667, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.38060176372528076, "target_z": -0.17968752518437028, "ce": 6.268836498260498, "genuineness": 4.645420074462891, "identity": 0.5556619167327881, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/9ca1560b87b2b9449783ccf1fbffe852bd514f934e29114c2066ae055ada6ac4.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-0", "key": "9cf58672fe3978a455f5873dd14ed24972e2b743bba52286db83f0f38736db23", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De deur staat nog open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6c01cd37b4f89871ddb1606154c1465c0a14efed5f9aadee31978784217d2584", "generation_seconds_batch": 20.351500272052363, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.117659091949463, "target_z": 2.3593749632444325, "ce": 5.538110733032227, "genuineness": 3.6789097785949707, "identity": 0.24943307042121887, "hypothesis": "De deur staat nog op. 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_Impatience_and_Irritability/9cf58672fe3978a455f5873dd14ed24972e2b743bba52286db83f0f38736db23.mp3" }, { "id": "emo_Impatience_and_Irritability-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-0", "key": "9e629d6ac17fe4e94553c96b7c96f52393f63619f751557265af03c7650110e1", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La puerta sigue abierta.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "f51a571369d427f60358b24bfecb0aebe2538973a13be4754a169856bedf959a", "generation_seconds_batch": 17.981368934968486, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.48749762773513794, "target_z": -0.023437484344850906, "ce": 6.0305562019348145, "genuineness": 4.281409740447998, "identity": 0.6020717620849609, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/9e629d6ac17fe4e94553c96b7c96f52393f63619f751557265af03c7650110e1.mp3" }, { "id": "emo_Impatience_and_Irritability-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-0", "key": "9e6d3b2bc2c5b6162ec2cfeee8541a199c6e91d9c9545233e434df0885ba906c", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Tür ist noch offen.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "c3a250530b47a11603825edc5c5a951dd3effdd000f426d796596c3c44c83259", "generation_seconds_batch": 19.041031430009753, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.6248903274536133, "target_z": 4.562499885649346, "ce": 5.700935363769531, "genuineness": 3.911123275756836, "identity": 0.46503162384033203, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/9e6d3b2bc2c5b6162ec2cfeee8541a199c6e91d9c9545233e434df0885ba906c.mp3" }, { "id": "emo_Impatience_and_Irritability-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-1", "key": "9f813c69f415e149561d225a144007571db8318f1e3992ea90514c78154a816d", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "4d8ea4f21f25b90e8b5c8a254c014742530cf3be0689f5a64e59e27f34243ce4", "generation_seconds_batch": 17.731988276005723, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.027845531702041626, "target_z": -0.6953124857061682, "ce": 6.38003396987915, "genuineness": 4.331617832183838, "identity": 0.4411386549472809, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/9f813c69f415e149561d225a144007571db8318f1e3992ea90514c78154a816d.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": "a08b9d768ac5b6d031691d04920b9e21f0987cb9e855e9146b5ebb23ff9cf1fa", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The keys are on the kitchen table.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f9d5af54a2373e155552c4970cbec439d6a59788752769965cc65f0873fc7415", "generation_seconds_batch": 18.247817363939248, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8931777477264404, "target_z": 2.0312498339192877, "ce": 5.43088436126709, "genuineness": 3.427868366241455, "identity": 0.13771848380565643, "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_Impatience_and_Irritability/a08b9d768ac5b6d031691d04920b9e21f0987cb9e855e9146b5ebb23ff9cf1fa.mp3" }, { "id": "emo_Impatience_and_Irritability-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-1", "key": "a19ba1dd2663ca854ebff3d33c6a9cb34f23119c9492cb35b850e5e63a60d084", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "4b8f9e693c360b2a8fffe31589067f202e5862157a306e80f04aaeac33969e1b", "generation_seconds_batch": 17.994874013005756, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11870697140693665, "target_z": -0.5625000163358077, "ce": 6.260893821716309, "genuineness": 4.557555198669434, "identity": 0.681763231754303, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/a19ba1dd2663ca854ebff3d33c6a9cb34f23119c9492cb35b850e5e63a60d084.mp3" }, { "id": "emo_Impatience_and_Irritability-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-1", "key": "a1b382ea5f47c696f08ced2eeaef7de5cd208505fdca678bb9c294c6b255dcf9", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I found the little box.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "cf6018e4d84e8e8aa388b74bd7101add9c1f6533beba6c7edcede0ba59575132", "generation_seconds_batch": 20.13860369194299, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23762860894203186, "target_z": -0.3886718622376502, "ce": 5.518253803253174, "genuineness": 3.6663577556610107, "identity": 0.39334970712661743, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/a1b382ea5f47c696f08ced2eeaef7de5cd208505fdca678bb9c294c6b255dcf9.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-1", "key": "a25f5aac2bbc15bd06725ef8d7ca76c4e4a4e42e75bc59d5921ec5ee4187c8c9", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "fd0fb98dba795d02503fa4c7613386755ba67cf787d5f57cdee9b6bad684ded6", "generation_seconds_batch": 14.069754650001414, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3739207983016968, "target_z": -0.18945311461995548, "ce": 6.205295085906982, "genuineness": 4.344170093536377, "identity": 0.5758032202720642, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/a25f5aac2bbc15bd06725ef8d7ca76c4e4a4e42e75bc59d5921ec5ee4187c8c9.mp3" }, { "id": "emo_Impatience_and_Irritability-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-1", "key": "a27054bfca06e6b86f44033d92daedefbffc9bd85739bcc6ef5d0f29d995de37", "bucket": "emo_Impatience_and_Irritability", "phase": "wording", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "754259eef16a03bb32043bc2e018c6aeaaf2f8148a4aa8a941e4dc48e952f222", "generation_seconds_batch": 14.662629490951076, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10801738500595093, "target_z": -0.5781250204197597, "ce": 6.292664527893066, "genuineness": 4.570107460021973, "identity": 0.5235410928726196, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/a27054bfca06e6b86f44033d92daedefbffc9bd85739bcc6ef5d0f29d995de37.mp3" }, { "id": "emo_Impatience_and_Irritability-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-1", "key": "a28f5b6ec1210ec8cb319103c6e135b38d1847271fb520303f220089675e5da5", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] He encontrado la cajita.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "64fb2a8a75599eab8e7ec35ce1683c157d0ff3769dc779849ecbaf8043db660a", "generation_seconds_batch": 21.43543142999988, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.004223227500915527, "target_z": -0.7421874979580241, "ce": 6.1020402908325195, "genuineness": 4.519899368286133, "identity": 0.7058587074279785, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/a28f5b6ec1210ec8cb319103c6e135b38d1847271fb520303f220089675e5da5.mp3" }, { "id": "emo_Impatience_and_Irritability-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-0", "key": "a2f4ddc14220c68af24e3ce8a4e616566afe96686c88c868fd1971381763a8d8", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Tür ist noch offen.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "61a10ba2d2126d43e2a246d8e844fc178e09cf33a16d487b89f45a718d469c21", "generation_seconds_batch": 19.4105680140201, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.710407018661499, "target_z": 4.687499918320961, "ce": 5.990842819213867, "genuineness": 4.306513786315918, "identity": 0.3884025812149048, "hypothesis": "Die Tür ist noch offen! Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/a2f4ddc14220c68af24e3ce8a4e616566afe96686c88c868fd1971381763a8d8.mp3" }, { "id": "emo_Impatience_and_Irritability-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-1", "key": "a30e1d84d0526234ed156a7effde458f379d1e455809fab1221e8f5951e3f5ed", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I found the little box.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "da1eb5c4da34fee577a759bcc0af8cb4a17e0493af6b6961ba65b19b1e5d4c33", "generation_seconds_batch": 18.841351971961558, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.006895601749420166, "target_z": -0.7460937163073965, "ce": 6.300607204437256, "genuineness": 4.432034492492676, "identity": 0.5841420292854309, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/a30e1d84d0526234ed156a7effde458f379d1e455809fab1221e8f5951e3f5ed.mp3" }, { "id": "emo_Impatience_and_Irritability-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-0", "key": "a3438c1205f99709ba060f723fe1a2d827c244110ead22bd0440614ec561a4de", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The door is still open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "810fbb5490bfd396d002d412a60b583656fbc356a1f8f50fca1e4adf44fa261e", "generation_seconds_batch": 23.466243161004968, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.064211130142212, "target_z": 2.281249899262519, "ce": 5.281959533691406, "genuineness": 3.440420389175415, "identity": 0.3388805091381073, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/a3438c1205f99709ba060f723fe1a2d827c244110ead22bd0440614ec561a4de.mp3" }, { "id": "emo_Impatience_and_Irritability-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-1", "key": "a350956c5468ffb62d8612044f3412f99041fe18471c4b54c22658346eb09626", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] He encontrado la cajita.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "50ecbda2e3e8d24378ba85948a29bd3ee930fba657f2128b8424c9e55d7bde43", "generation_seconds_batch": 17.91355488402769, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4006447494029999, "target_z": -0.15039062619115265, "ce": 5.871703147888184, "genuineness": 4.174716949462891, "identity": 0.62205970287323, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/a350956c5468ffb62d8612044f3412f99041fe18471c4b54c22658346eb09626.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": "a3a207562e90f4fe69c2a9c6be2f60be99ded9b9ecaee5c318a81943371272fa", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "028bbf5af718f6e505d0760241ead026df1e6d7fdf29527d6403c055a684b423", "generation_seconds_batch": 13.601456040982157, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.55593204498291, "target_z": 3.0, "ce": 5.998785495758057, "genuineness": 3.785602569580078, "identity": 0.5589596629142761, "hypothesis": "Chacun a déplacé la petite chaise bleue. Elle était ici, près de la grande bibliothèque. Nous la remettrons après le déjeuner.", "wer": 0.047619047619047616, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/a3a207562e90f4fe69c2a9c6be2f60be99ded9b9ecaee5c318a81943371272fa.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-1", "key": "a3f56ed0d6ab4981c488bc68943b1ab4ed9f005b412070f7166b8c71216e6207", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "3a9f992b9ebc6e341d88c217e6a31ba7ad3052ffc01aad11f98325615c1092d8", "generation_seconds_batch": 18.30818030098453, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2416372001171112, "target_z": -0.38281249115143745, "ce": 6.173524379730225, "genuineness": 4.2249250411987305, "identity": 0.8278006911277771, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/a3f56ed0d6ab4981c488bc68943b1ab4ed9f005b412070f7166b8c71216e6207.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-1", "key": "a42f680e04274c53f12c9a203938548629a818a061f6c4be5631239b276d1f74", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "f2cbb810a3c9ceb5241e2ded6fdf92e7b9b694779c08844cd0b3af755a84db9d", "generation_seconds_batch": 18.180310201947577, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2590077519416809, "target_z": -0.3574218976319003, "ce": 6.181467056274414, "genuineness": 4.532451152801514, "identity": 0.5974072217941284, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/a42f680e04274c53f12c9a203938548629a818a061f6c4be5631239b276d1f74.mp3" }, { "id": "emo_Impatience_and_Irritability-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-0", "key": "a433effe10f0defdd11c99d83a6787c31ce4c5d81624efe34dd9e9644ae688b6", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Tür ist noch offen.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "1701ad823ae71437c6e0b1743ab6a3718639f1d1344f9ffdf40b10a5a10114e7", "generation_seconds_batch": 13.109840751974843, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2870679199695587, "target_z": -0.31640625646625725, "ce": 5.935244083404541, "genuineness": 4.494794845581055, "identity": 0.5066209435462952, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/a433effe10f0defdd11c99d83a6787c31ce4c5d81624efe34dd9e9644ae688b6.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-1", "key": "a45d5750433afdd051d0ed9c69f7b353836a4f0fc69957ca2bceaeea52868ba9", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "7db1da5613da81f769c3e75984feb5a66c0dabec94420c459c8b34cc8d72ce32", "generation_seconds_batch": 18.147168789990246, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.00956803560256958, "target_z": -0.750000021781077, "ce": 6.205295085906982, "genuineness": 4.607763767242432, "identity": 0.7349236011505127, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/a45d5750433afdd051d0ed9c69f7b353836a4f0fc69957ca2bceaeea52868ba9.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-0", "key": "a487f5a27102cceb33e4a94fc78d37bbbb4f444e0f9524aede189c45ac9725f1", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De deur staat nog open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "9323a77ad590a9256d474075d2bd3edce7866f1345286c0510f5d94a7bcd99f9", "generation_seconds_batch": 13.055920723942108, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0749008655548096, "target_z": 2.2968751211572407, "ce": 5.9431867599487305, "genuineness": 3.8169827461242676, "identity": 0.695084810256958, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/a487f5a27102cceb33e4a94fc78d37bbbb4f444e0f9524aede189c45ac9725f1.mp3" }, { "id": "emo_Impatience_and_Irritability-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-0", "key": "a4b2d9dda17b07522cc358e954f0fff1363cf00655d23bddba572f12cf4d064f", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La puerta sigue abierta.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "25270c7ea42132789c68146e8f8831aef0737ddce62ab065f26effe94fe87ed0", "generation_seconds_batch": 13.114055382087827, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21758562326431274, "target_z": -0.41796876123086785, "ce": 6.205295085906982, "genuineness": 4.406930446624756, "identity": 0.5945152640342712, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/a4b2d9dda17b07522cc358e954f0fff1363cf00655d23bddba572f12cf4d064f.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-0", "key": "a4b39809ce8fe8d763235917b967d9dc0b273724e6a2fe5a0e8e07b267e1e66c", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La porte est encore ouverte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "1e185891070732b218de0f827672edb4ac9cc8d6206f913df1c0d5865a98dd11", "generation_seconds_batch": 19.88298625696916, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13474136590957642, "target_z": -0.5390624884288029, "ce": 6.197352409362793, "genuineness": 4.425758361816406, "identity": 0.46355727314949036, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/a4b39809ce8fe8d763235917b967d9dc0b273724e6a2fe5a0e8e07b267e1e66c.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-0", "key": "a4fdca3e58ef05cecfbeaf61de2b03d35e70326d0731e6ffc50d6d6c78b581d0", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La porte est encore ouverte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "4cadd4d2adfc47b20ca6f70d2321ffe4555f9a30c84b4d6ddeea967fbd728aeb", "generation_seconds_batch": 18.267728995066136, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2590077519416809, "target_z": -0.3574218976319003, "ce": 6.022613525390625, "genuineness": 4.218649387359619, "identity": 0.6512404084205627, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/a4fdca3e58ef05cecfbeaf61de2b03d35e70326d0731e6ffc50d6d6c78b581d0.mp3" }, { "id": "emo_Impatience_and_Irritability-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-1", "key": "a515af1b0ec26a7dfb43ece82b5bb1001c2b6632a0108e78298311be67af73bd", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] He encontrado la cajita.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "628bbece1a2f12ab14abc88b26a366ff7104df7737b048adf5aa5af9ab351cce", "generation_seconds_batch": 19.338468339992687, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4407306909561157, "target_z": -0.09179687176687139, "ce": 4.72100830078125, "genuineness": 3.8044304847717285, "identity": 0.6164032220840454, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/a515af1b0ec26a7dfb43ece82b5bb1001c2b6632a0108e78298311be67af73bd.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-0", "key": "a519d54d51820507b56959f9378431a32acfd4d0738ac956a1707d1ab3f3794c", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La porte est encore ouverte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "f7a692f409a5acb7acfa04c9743cb0d01b4365860c9a4cc2eaa1b173a3c402f0", "generation_seconds_batch": 18.14116199896671, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15612053871154785, "target_z": -0.507812480260899, "ce": 5.935244083404541, "genuineness": 3.9299514293670654, "identity": 0.7818750143051147, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/a519d54d51820507b56959f9378431a32acfd4d0738ac956a1707d1ab3f3794c.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": "a5b986bd1bb0daf1b25a598389452cd2cc33b4f1aaed7da07e1b1b6054ca1a9b", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "a7e52ae419ed8cb3784b27aed3a994ed4c23745d4aaf2268905467c53a7f551e", "generation_seconds_batch": 13.156847144011408, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.791102886199951, "target_z": 3.3437500027226346, "ce": 5.426913261413574, "genuineness": 3.8797430992126465, "identity": 0.5097570419311523, "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_Impatience_and_Irritability/a5b986bd1bb0daf1b25a598389452cd2cc33b4f1aaed7da07e1b1b6054ca1a9b.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-0", "key": "a5d4e9382dd35889e35eea48aefe559db4eeb6a50495a29812391825e31ac983", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La porte est encore ouverte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "bfdd84618f01a302960246337eeb98160db5f463f6dbb01e8866e33d01cb1684", "generation_seconds_batch": 17.823958347085863, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.28172314167022705, "target_z": -0.3242187367271562, "ce": 5.959072113037109, "genuineness": 4.080576419830322, "identity": 0.6653096079826355, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/a5d4e9382dd35889e35eea48aefe559db4eeb6a50495a29812391825e31ac983.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": "a5ed04f6a1ed37fb4497b6e6899d1ffd466cd3ed7d24361b0f1ec7863909f542", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "86b214aa2fa5130b4c9f7593c0300de08bcbf8c82af10c6c34de79e07127751c", "generation_seconds_batch": 18.35052423097659, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.897998571395874, "target_z": 3.49999978218923, "ce": 5.065521717071533, "genuineness": 3.452972412109375, "identity": 0.10106281191110611, "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_Impatience_and_Irritability/a5ed04f6a1ed37fb4497b6e6899d1ffd466cd3ed7d24361b0f1ec7863909f542.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-1", "key": "a6171b8eae6804df90588405f8ba9f07d63670898233c54d3881755be2e6eaea", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "e6590d0377fe651091c569e3a35ae1b5a3ae96fbaed6ed5c28e110e3668ecd4a", "generation_seconds_batch": 13.223683195072226, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.00956803560256958, "target_z": -0.750000021781077, "ce": 5.871703147888184, "genuineness": 4.457139015197754, "identity": 0.49927008152008057, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/a6171b8eae6804df90588405f8ba9f07d63670898233c54d3881755be2e6eaea.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-1", "key": "a6924018d418aeb99e48affaf5357c2eeb6f13e97a2c3b46c9d4dd0cdb64d519", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "a2b591bfcf9f73a54e1ee641fb3e0e6bcdff8fd0b50a6c113e9f5c270221554f", "generation_seconds_batch": 19.083424907992594, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.049224674701690674, "target_z": -0.6640625211004183, "ce": 6.24500846862793, "genuineness": 4.65797233581543, "identity": 0.561721682548523, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/a6924018d418aeb99e48affaf5357c2eeb6f13e97a2c3b46c9d4dd0cdb64d519.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": "a6f7a56cec2c1e8bb3046cb6abc3d00c6c9c37e5432706259bfc7355ff9365af", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The road turns left behind the bridge.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "21b85e73a2a656aa67c4eff418a0de77faca69549152bd3a809c7b8cf9562859", "generation_seconds_batch": 20.801278779981658, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2197340726852417, "target_z": 1.0468749686897019, "ce": 5.4944257736206055, "genuineness": 3.3243136405944824, "identity": 0.3001618981361389, "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_Impatience_and_Irritability/a6f7a56cec2c1e8bb3046cb6abc3d00c6c9c37e5432706259bfc7355ff9365af.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": "a70266fa816a4340035a74297c3500055add5d575fc3da17144b8f9350453271", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0e250579004d4da25864a7c724bea8a9c3eb86217ed7559753a6463dfcdb5d59", "generation_seconds_batch": 13.270713496953249, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.588000774383545, "target_z": 3.0468749686897016, "ce": 5.967014789581299, "genuineness": 3.7793264389038086, "identity": 0.24100208282470703, "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_Impatience_and_Irritability/a70266fa816a4340035a74297c3500055add5d575fc3da17144b8f9350453271.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-0", "key": "a7063c1e0a7fa77cd80b6faab98634a67788252973dbdb9d923c67515d01fb88", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De deur staat nog open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "75b7786e6ec0af270aa7bcb8829733fca80c5680b08078335672133f55b3750a", "generation_seconds_batch": 17.868345235008746, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0647351741790771, "target_z": 0.8203125619399377, "ce": 6.09409761428833, "genuineness": 4.068024158477783, "identity": 0.6873724460601807, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/a7063c1e0a7fa77cd80b6faab98634a67788252973dbdb9d923c67515d01fb88.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-1", "key": "a735a0468d920fce5631a636dc9aae81e0228268a4cc3f82377b626ea1a74dd0", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "1dbcd895f1ef79a0ddd6dcbd3a81cb5b3fdcfd0a550ffc262b569f2951172511", "generation_seconds_batch": 17.85261665796861, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19086167216300964, "target_z": -0.4570312496596707, "ce": 5.990842819213867, "genuineness": 4.632867813110352, "identity": 0.47138097882270813, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/a735a0468d920fce5631a636dc9aae81e0228268a4cc3f82377b626ea1a74dd0.mp3" }, { "id": "emo_Impatience_and_Irritability-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-0", "key": "a78d2c066188d822933932449c294be6042e7609b759dbbfd7615edca5d250e7", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The door is still open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "277e0b82f3b654a8c4828a438e43e24ae47c3eab473fdc8243a2e9349e36b7cb", "generation_seconds_batch": 18.224620430963114, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6900758743286133, "target_z": 1.734375148383587, "ce": 6.09409761428833, "genuineness": 3.4843525886535645, "identity": 0.3418198227882385, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/a78d2c066188d822933932449c294be6042e7609b759dbbfd7615edca5d250e7.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-0", "key": "a82186ba7a275d7e8b012e39affa4d2e3edb0d71a15a1e9d6e4b1ea44bf9ae51", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La porte est encore ouverte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "9dec942b3732be1937376bbca4caaa269c5e21adeb3da5c63d6ead4c25aa6883", "generation_seconds_batch": 17.91423213807866, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18551689386367798, "target_z": -0.46484372992056966, "ce": 6.022613525390625, "genuineness": 4.18099308013916, "identity": 0.49232518672943115, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/a82186ba7a275d7e8b012e39affa4d2e3edb0d71a15a1e9d6e4b1ea44bf9ae51.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_Impatience_and_Irritability", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": "bcffe1ff7c8de2145a4b290d2b3d20acc68fbea9d560cf2cc80fcbb19bd0f4cd", "generation_seconds_batch": 14.175500835990533, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1694824993610382, "target_z": -0.48828125782757453, "ce": 6.078212261199951, "genuineness": 4.20609712600708, "identity": 0.47134608030319214, "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_Impatience_and_Irritability/a8bd001b1fcafd2f49b65d73e6ed12567e4c9664909a4d08700c9febfd977540.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-0", "key": "a91e27438f36826ef6835032b0a88fc1ac895aa6dbdeb60d6f3ac8f116f8634b", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De deur staat nog open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "81d7e7489bd9e50941f2e06e7e01239d6d436205812f60a924b53fa9eca32e7b", "generation_seconds_batch": 19.71386455593165, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6418284773826599, "target_z": 0.20214843316080106, "ce": 5.839932441711426, "genuineness": 4.293961524963379, "identity": 0.5915704965591431, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/a91e27438f36826ef6835032b0a88fc1ac895aa6dbdeb60d6f3ac8f116f8634b.mp3" }, { "id": "emo_Impatience_and_Irritability-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-1", "key": "a940403063e0673dfc596140917beae00c49bbb77a6100150216f64ccf575dd1", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "b40d1cd29e9109e0724ce8c307ef2fb2593bcac6c777acff4f286211c0278c04", "generation_seconds_batch": 14.483517669024877, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.014483541250228882, "target_z": -0.7148437517016466, "ce": 6.419747352600098, "genuineness": 4.105680465698242, "identity": 0.5872050523757935, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/a940403063e0673dfc596140917beae00c49bbb77a6100150216f64ccf575dd1.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_Impatience_and_Irritability", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": "0d62eefad86c4c06a5a04bce499a7229e2128b653d61ba1758d7b3bf74822e48", "generation_seconds_batch": 14.516162903048098, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12939655780792236, "target_z": -0.5468750122518559, "ce": 6.086154937744141, "genuineness": 4.250029563903809, "identity": 0.7076764702796936, "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_Impatience_and_Irritability/a94b7d5da78ff217f8e5a4f7ae4520900bef0ad764d0e4ee898e69de10c28aea.mp3" }, { "id": "emo_Impatience_and_Irritability-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-1", "key": "a96e9c4010ef2ef2c909d3c40962d5d28faeaf5ee770a227b81b1576c270d1e0", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] He encontrado la cajita.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "9aaaaf71ea6773a942e5f6de6209f58bfde6f9b7376e29fb525ff1ffc90d7580", "generation_seconds_batch": 13.242934221983887, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1962064504623413, "target_z": -0.4492187693987717, "ce": 5.895530700683594, "genuineness": 4.356721878051758, "identity": 0.5413296818733215, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/a96e9c4010ef2ef2c909d3c40962d5d28faeaf5ee770a227b81b1576c270d1e0.mp3" }, { "id": "emo_Impatience_and_Irritability-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-0", "key": "aa0dff2bfa85112e61667621bfd22f096a69db3ae71aaab05955fcd7e7b38520", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The door is still open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "2ed1ce59785ca072c1871a457bee12a3ad1b1a8c439b420e0844e07451bce13d", "generation_seconds_batch": 19.314413256011903, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11068978905677795, "target_z": -0.5742187585082332, "ce": 6.181467056274414, "genuineness": 4.042920112609863, "identity": 0.41164278984069824, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/aa0dff2bfa85112e61667621bfd22f096a69db3ae71aaab05955fcd7e7b38520.mp3" }, { "id": "emo_Impatience_and_Irritability-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-0", "key": "aae82319ba2f561f058208ebae5fdebad76ba4bc9b9c83ad1a01fab777f91622", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La puerta sigue abierta.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "c9f8983a5e8e8735e2d88cff76aa2cc8538d4d3b06a970c51189625bc828b6ba", "generation_seconds_batch": 18.394722539000213, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6144364476203918, "target_z": 0.1621094119257321, "ce": 5.919358730316162, "genuineness": 3.9676074981689453, "identity": 0.6464659571647644, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/aae82319ba2f561f058208ebae5fdebad76ba4bc9b9c83ad1a01fab777f91622.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-0", "key": "ab0e147846758cbba3355baf1ba727d157d859ac23a9c54dffb6df426a0780a9", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La porte est encore ouverte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "ee033dc1ae848a3cab3e6227ab88b8151fc77d4e1076f5aabc165de0e0ba1158", "generation_seconds_batch": 17.823958347085863, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20689603686332703, "target_z": -0.43359376531481975, "ce": 5.8875885009765625, "genuineness": 4.15588903427124, "identity": 0.6634045839309692, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/ab0e147846758cbba3355baf1ba727d157d859ac23a9c54dffb6df426a0780a9.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_Impatience_and_Irritability", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": "aa4dda2efdbed48f258aaee90270275ae489b945c4a99f543f15a12d8be8a5e3", "generation_seconds_batch": 13.74647383892443, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10801738500595093, "target_z": -0.5781250204197597, "ce": 6.435632705688477, "genuineness": 4.143336772918701, "identity": 0.3647051751613617, "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_Impatience_and_Irritability/ab7a94299f968552a7b966fa3391724b652d8e20483888a7767196f29a7f4a69.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": "ac0bf0744c66b96b7b65859188d78f8914a3b2aba3f6f3948970232e7efa19b9", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a1f0139218b1bf30caaa68706c4c5932353724b94cf0a9d74cda991c84ff3933", "generation_seconds_batch": 15.408313142019324, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8824882507324219, "target_z": 2.015624960521798, "ce": 5.426913261413574, "genuineness": 3.553389072418213, "identity": 0.2663149833679199, "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_Impatience_and_Irritability/ac0bf0744c66b96b7b65859188d78f8914a3b2aba3f6f3948970232e7efa19b9.mp3" }, { "id": "emo_Impatience_and_Irritability-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-1", "key": "ac70af954d8f41b679ff15eb016a989ce110bf7c1361642655b6919c5e042d70", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I found the little box.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "9e8496e86b66eb02ae7ada2d30088ada149da89d4d372af1f406f13bb8dadf90", "generation_seconds_batch": 14.397804271080531, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07060384750366211, "target_z": -0.6328125129325145, "ce": 6.165581703186035, "genuineness": 4.15588903427124, "identity": 0.42575812339782715, "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_Impatience_and_Irritability/ac70af954d8f41b679ff15eb016a989ce110bf7c1361642655b6919c5e042d70.mp3" }, { "id": "emo_Impatience_and_Irritability-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-0", "key": "acd4cfd946264fd6292b4992c6438d3e0f8612c54423e8ffb972122c7e447a89", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The door is still open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "65cf8b6cdd37177c636d23e8f4078eeb1e25acc567e9672ed8e7e5ba729f4c5e", "generation_seconds_batch": 19.293493896955624, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16280150413513184, "target_z": -0.4980468908253138, "ce": 6.205295085906982, "genuineness": 3.9425034523010254, "identity": 0.31134670972824097, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/acd4cfd946264fd6292b4992c6438d3e0f8612c54423e8ffb972122c7e447a89.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-0", "key": "ad658472112842134e68f17e9142b6085233b39dcb2a5c710dc0bc58303c4b16", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De deur staat nog open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e3c10fb3840f08b6305db247eac792205677cd7ff9e5de39da1daa259e5c1571", "generation_seconds_batch": 19.551935908966698, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3373194932937622, "target_z": 1.2187499700510191, "ce": 5.645336627960205, "genuineness": 3.6224255561828613, "identity": 0.46451374888420105, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/ad658472112842134e68f17e9142b6085233b39dcb2a5c710dc0bc58303c4b16.mp3" }, { "id": "emo_Impatience_and_Irritability-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-0", "key": "adc20e0eacb91ec397f366972adb2eae16e935deb7e54f92039d83d6bc0fb25a", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La puerta sigue abierta.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "d0f2e3b34998433a6e2afc63e7814288c1f881654dc39e0168f18058789f1044", "generation_seconds_batch": 14.064703266019933, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4704153537750244, "target_z": 2.8749999673283844, "ce": 5.998785495758057, "genuineness": 3.625563621520996, "identity": 0.638852596282959, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/adc20e0eacb91ec397f366972adb2eae16e935deb7e54f92039d83d6bc0fb25a.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_Impatience_and_Irritability", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": "a811c7746f5207097ed469775a8f01f25e51d64f7089de4c47fc0a643068945b", "generation_seconds_batch": 16.42797673807945, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.27103355526924133, "target_z": -0.33984374081110813, "ce": 6.213237762451172, "genuineness": 4.413206577301025, "identity": 0.6298089027404785, "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_Impatience_and_Irritability/adcc0121d6c11de6953f8243f84ad890832f75283c96342c1db246fddc443438.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-0", "key": "adcfdd0d9fed5a06f5f51f3bdd325ad0852b35c1610bf70c71af5621accfedd2", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La porte est encore ouverte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "0dc0938f2ebed13d7b57878b0eb15bc7bd02e798501460cce12f6a849c5772b4", "generation_seconds_batch": 20.85946439707186, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5516351461410522, "target_z": 0.07031254015886072, "ce": 5.522225379943848, "genuineness": 4.218649387359619, "identity": 0.4460650682449341, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/adcfdd0d9fed5a06f5f51f3bdd325ad0852b35c1610bf70c71af5621accfedd2.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-1", "key": "adda88aed08de053f6ea62d2d07f41e8b2c103cf0c50017a86a6023605ac5f22", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "b796699ea3d27653f6947af777e3aeabdca56936a5dea1aba78821d19cd1b2aa", "generation_seconds_batch": 14.075085149961524, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2352445125579834, "target_z": 2.53124996460575, "ce": 5.863759994506836, "genuineness": 3.7542223930358887, "identity": 0.12782755494117737, "hypothesis": "Ik heb het kleine toosje 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_Impatience_and_Irritability/adda88aed08de053f6ea62d2d07f41e8b2c103cf0c50017a86a6023605ac5f22.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_Impatience_and_Irritability", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": "ffa175df98dc8190af511ba4144348c6a9a8a54d26d5be20fe60ab8161e9bda0", "generation_seconds_batch": 14.830674357013777, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0973278284072876, "target_z": -0.5937499809415576, "ce": 6.403861999511719, "genuineness": 4.124508857727051, "identity": 0.18555603921413422, "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_Impatience_and_Irritability/ae3130a5db36c2790a31e23135fde257111c56fa9c5b8061c1f3e51a8cb61258.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": "ae6d760569627296faf4562244997aebe201c007db1bca8c4d160928ac6d6606", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "456b0d7217fbd8e2a7d133cf3ed89e51663e356ff427a8635ba02dceb5ab6f7c", "generation_seconds_batch": 18.4100108880084, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.603511095046997, "target_z": 4.531249790357134, "ce": 5.649308204650879, "genuineness": 3.7918784618377686, "identity": 0.37909191846847534, "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_Impatience_and_Irritability/ae6d760569627296faf4562244997aebe201c007db1bca8c4d160928ac6d6606.mp3" }, { "id": "emo_Impatience_and_Irritability-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-1", "key": "ae6e7286a1d249e24e189976be03bfcbf95d0a3c9fb22c87f252729ebe1eb804", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "3b62dbef11df4faa2a5221c9c35f7b3a2b9aa1f386cee4f43e99389d9700bdd6", "generation_seconds_batch": 23.330887370975688, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2304236888885498, "target_z": 1.0625000163358078, "ce": 5.80021858215332, "genuineness": 4.042920112609863, "identity": 0.5501828193664551, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/ae6e7286a1d249e24e189976be03bfcbf95d0a3c9fb22c87f252729ebe1eb804.mp3" }, { "id": "emo_Impatience_and_Irritability-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-1", "key": "ae833b000fa6141f8bcc16ab9e52f473129a88c6f344952d1a4cffeee8105d66", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I found the little box.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "8f7ca8ecb6bec52565c874859a2d5df07c0fd4a4a986abc47ae52889484100e8", "generation_seconds_batch": 12.991034857928753, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0469815731048584, "target_z": -0.8046875142938318, "ce": 6.260893821716309, "genuineness": 4.344170093536377, "identity": 0.4327148497104645, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/ae833b000fa6141f8bcc16ab9e52f473129a88c6f344952d1a4cffeee8105d66.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-1", "key": "aecb3439703de72bc3d327b8ae7303579669fdbda8ced89f7042e718ceb47885", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "9505c5df6d2829fe2b279eb81faee69ca1989ced4384280c7196b6c0c36fdb3a", "generation_seconds_batch": 17.973528189002536, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23896479606628418, "target_z": -0.38671875306296394, "ce": 5.8875885009765625, "genuineness": 4.432034492492676, "identity": 0.614899218082428, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/aecb3439703de72bc3d327b8ae7303579669fdbda8ced89f7042e718ceb47885.mp3" }, { "id": "emo_Impatience_and_Irritability-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-1", "key": "af0b8b9c11281f382f3f08c4b992f2c2a4ca88669e926a2f9c46d23ac5b261e5", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I found the little box.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "7f8e8e3be73340b7d8061516cf63f6643374908a5f1731b3ba02ef090e81b4d7", "generation_seconds_batch": 13.218400561949238, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2870679199695587, "target_z": -0.31640625646625725, "ce": 5.561938762664795, "genuineness": 3.823258876800537, "identity": 0.30724769830703735, "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_Impatience_and_Irritability/af0b8b9c11281f382f3f08c4b992f2c2a4ca88669e926a2f9c46d23ac5b261e5.mp3" }, { "id": "emo_Impatience_and_Irritability-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-0", "key": "af13103eaf176484cb9069081289e89ca09518bdc569b16c38291506ac4b82a6", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Tür ist noch offen.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "413aa0a91ca1432ed08fc44486ad4bc7e4263797854b42363663770c0c6f8604", "generation_seconds_batch": 17.9353584269993, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7055861949920654, "target_z": 3.218749970051019, "ce": 5.673136234283447, "genuineness": 4.068024158477783, "identity": 0.39263737201690674, "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_Impatience_and_Irritability/af13103eaf176484cb9069081289e89ca09518bdc569b16c38291506ac4b82a6.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-0", "key": "af14284996c52285f8c1fa8e3febe72719b5d07b3d8d0a9bc4af92f67b8b11f8", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La porte est encore ouverte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "1f31b88ed20bbeb7445791a55ea0f357acb8cbff30c6ee1a003ad92251fdec06", "generation_seconds_batch": 13.625028640963137, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3031023144721985, "target_z": -0.2929687285592523, "ce": 6.165581703186035, "genuineness": 4.595211505889893, "identity": 0.709480345249176, "hypothesis": "La porte t'est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/af14284996c52285f8c1fa8e3febe72719b5d07b3d8d0a9bc4af92f67b8b11f8.mp3" }, { "id": "emo_Impatience_and_Irritability-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-0", "key": "af1b63bbf3aaf734ad59ce7e0960ef78fde47eca627b2a4a5ea4746b4e592407", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Tür ist noch offen.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "66601d41bb1f77e38b62787ee0d02971d92598f4b4bd810eb165df79fd77653c", "generation_seconds_batch": 19.554461485007778, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2731820344924927, "target_z": 1.1250000326716154, "ce": 6.260893821716309, "genuineness": 4.632867813110352, "identity": 0.5839248299598694, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/af1b63bbf3aaf734ad59ce7e0960ef78fde47eca627b2a4a5ea4746b4e592407.mp3" }, { "id": "emo_Impatience_and_Irritability-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-1", "key": "af3380025f293b034c9de1d5e5abb0df64a2e3dbdc014c16d8ace87e030c9d49", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I found the little box.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "be050f77814a97e9223ba395ac396e940a257f83ef502240f898c522b331ed8d", "generation_seconds_batch": 19.323610141989775, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.02025759220123291, "target_z": -0.7656249823028749, "ce": 6.252951145172119, "genuineness": 4.193545341491699, "identity": 0.491425484418869, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/af3380025f293b034c9de1d5e5abb0df64a2e3dbdc014c16d8ace87e030c9d49.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-1", "key": "af83e5dec38d95a48a4ba92304b6b3ca167ead4efbf118aae529d7cc681f203f", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "9ff0851e556a24b72a25363944e9b9a8ad166d271113952262b37028365431c3", "generation_seconds_batch": 18.92247041501105, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1545486450195312, "target_z": 3.8749998802040766, "ce": 5.462655067443848, "genuineness": 3.5565271377563477, "identity": 0.42592060565948486, "hypothesis": "Ik 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_Impatience_and_Irritability/af83e5dec38d95a48a4ba92304b6b3ca167ead4efbf118aae529d7cc681f203f.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": "afbbe475c439d18d5ad87c423585407184bb96c8c540532960a133af31f3c150", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "256984155add41f329b1dbb7baa3f395a03931155cb7edf5a661f66b5523e8bf", "generation_seconds_batch": 13.203592056990601, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7809371948242188, "target_z": 1.8671874435053315, "ce": 4.964252471923828, "genuineness": 3.525146961212158, "identity": 0.6048260927200317, "hypothesis": "Ik schreef het nummer op de envelop. Lees het goed en controleer de laatste twee cijfers. Bel me wanneer je even tijd hebt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/afbbe475c439d18d5ad87c423585407184bb96c8c540532960a133af31f3c150.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-0", "key": "afc39eb804914040d82190a18c054a90850ffd8ee04cb92ee97691469836707a", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De deur staat nog open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "4ccd31949131e24a51b63277fd38d053f688470a58e176a12a20211686b9ad24", "generation_seconds_batch": 18.448496566037647, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.299381971359253, "target_z": 2.6249999019851535, "ce": 5.478540420532227, "genuineness": 3.5816311836242676, "identity": 0.5857356786727905, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar, wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/afc39eb804914040d82190a18c054a90850ffd8ee04cb92ee97691469836707a.mp3" }, { "id": "emo_Impatience_and_Irritability-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-1", "key": "afd31c751693e080a7ee6ddf98f16000542098510d741b005c1f1ba347320662", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I found the little box.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "cb6a6ecc45a7e741a1197f6a87d985a28426f9bd196c86ac53c09e8dc534d0dd", "generation_seconds_batch": 17.962664840044454, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0469815731048584, "target_z": -0.8046875142938318, "ce": 6.205295085906982, "genuineness": 4.293961524963379, "identity": 0.6932241916656494, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/afd31c751693e080a7ee6ddf98f16000542098510d741b005c1f1ba347320662.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-0", "key": "b02d7edd470ced4de786b070bce56d4da8cbc50623c786581b17ebd16cdce0ef", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La porte est encore ouverte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "dcf904122dada5babd724dfbf060d7fa4e5d856984b844ebc08d480fbe6485a7", "generation_seconds_batch": 13.143054000101984, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4474116861820221, "target_z": -0.08203123876913217, "ce": 6.157639026641846, "genuineness": 4.6705241203308105, "identity": 0.27287083864212036, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/b02d7edd470ced4de786b070bce56d4da8cbc50623c786581b17ebd16cdce0ef.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-1", "key": "b0408c82ab4fd5a3243dcef0efbf43ba4fdc1c2cb5161079f58a17a2c48ec9d5", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "d866ef3e8cd7482032e68301b0a36eba1e4397f8cca431bb10c3eddb735dde6c", "generation_seconds_batch": 18.001885836943984, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14810332655906677, "target_z": -0.5195312659954784, "ce": 6.09409761428833, "genuineness": 4.570107460021973, "identity": 0.46732836961746216, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/b0408c82ab4fd5a3243dcef0efbf43ba4fdc1c2cb5161079f58a17a2c48ec9d5.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-0", "key": "b0a233a7515749b0a5eec9c8da65e2cac8a44b1c56941c645ec1984731692a21", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De deur staat nog open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "9a1a8c9886b6e22256ae29ff9c0355a51df965114a306e8a552e1ea7f8d0edc7", "generation_seconds_batch": 18.29708983609453, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7007653713226318, "target_z": 1.750000021781077, "ce": 5.927301406860352, "genuineness": 3.961331605911255, "identity": 0.6250002384185791, "hypothesis": "De deur 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_Impatience_and_Irritability/b0a233a7515749b0a5eec9c8da65e2cac8a44b1c56941c645ec1984731692a21.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-0", "key": "b0a4a8bd5ddc3ba07d4c89bff6962f088ce7d768e947f501e390badf3c3940dd", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La porte est encore ouverte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "2b560696c249228d19ef1366ed459e1253d0f2005130065edeacecc0781012f1", "generation_seconds_batch": 17.91423213807866, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19353407621383667, "target_z": -0.4531249877481442, "ce": 6.062326908111572, "genuineness": 4.193545341491699, "identity": 0.7869075536727905, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/b0a4a8bd5ddc3ba07d4c89bff6962f088ce7d768e947f501e390badf3c3940dd.mp3" }, { "id": "emo_Impatience_and_Irritability-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-0", "key": "b0d6414f15e68a88b6a5b8096154ff0d3389d5941b8781726b044fb090f98fbb", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Tür ist noch offen.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "4699053687634c8f9650880a892ea66f51c9dc0e97d7d3dda2708c838b76ee7f", "generation_seconds_batch": 17.479108887026086, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18818926811218262, "target_z": -0.46093751157119717, "ce": 6.078212261199951, "genuineness": 4.406930446624756, "identity": 0.3668156862258911, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/b0d6414f15e68a88b6a5b8096154ff0d3389d5941b8781726b044fb090f98fbb.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-0", "key": "b12eefe3a71612e5d66ec9e83ee172ae75c1e7a82f0b59c8dc9fa9c346393ffb", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De deur staat nog open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "e3e062f98e15d8970d31265f5e3944cbee4f370fbc5dadf1024e33b31a3f18e1", "generation_seconds_batch": 19.71386455593165, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.198354959487915, "target_z": 1.015625047646106, "ce": 5.8875885009765625, "genuineness": 4.042920112609863, "identity": 0.5558297634124756, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/b12eefe3a71612e5d66ec9e83ee172ae75c1e7a82f0b59c8dc9fa9c346393ffb.mp3" }, { "id": "emo_Impatience_and_Irritability-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-0", "key": "b1430a7a4b2a97bf123a8eb13c8d7884a98d1a9816dcc7dc8b4d7f012b65ce92", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Tür ist noch offen.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "c17ef60eb0a6b1a54c090c5b00daac862f6493840701d9e7a17961d5266052a2", "generation_seconds_batch": 18.121031234040856, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6585309505462646, "target_z": 0.2265624938740721, "ce": 6.395919322967529, "genuineness": 4.6203155517578125, "identity": 0.5050860643386841, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/b1430a7a4b2a97bf123a8eb13c8d7884a98d1a9816dcc7dc8b4d7f012b65ce92.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-0", "key": "b171677adfdfb3bb813a40b3915cb854f75f3a06695eae15a1801cd10efe8eee", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La porte est encore ouverte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "f8556a7c7fb1cb296280ec0116ba482d26ed476c7e5cb83cd30b89cfbcc8e3a6", "generation_seconds_batch": 18.47156018705573, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2790507376194, "target_z": -0.32812499863868266, "ce": 5.855817794799805, "genuineness": 4.582659721374512, "identity": 0.6335067749023438, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/b171677adfdfb3bb813a40b3915cb854f75f3a06695eae15a1801cd10efe8eee.mp3" }, { "id": "emo_Impatience_and_Irritability-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-0", "key": "b1f40c30f3d179f730a8b6ad278d14e6dc7679641a4883c11f3607cddd81ea64", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Tür ist noch offen.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "19ca5c1af6f24f4797c52e2a84398513998dd4266fe0d47d90688b12979efff9", "generation_seconds_batch": 18.952459497959353, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.838681936264038, "target_z": 4.874999793079769, "ce": 5.752562999725342, "genuineness": 3.8797430992126465, "identity": -0.04814425855875015, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/b1f40c30f3d179f730a8b6ad278d14e6dc7679641a4883c11f3607cddd81ea64.mp3" }, { "id": "emo_Impatience_and_Irritability-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-1", "key": "b225e72158d8f430387f635711725621435a8f7bf864c972beffc684930501a1", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I found the little box.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "9f270fba2b2abad06020e9de4d7926e8c79b4db2d905d3432e58a04dc08872c4", "generation_seconds_batch": 17.86286833998747, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05991426110267639, "target_z": -0.6484375170164665, "ce": 6.260893821716309, "genuineness": 4.306513786315918, "identity": 0.41328197717666626, "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_Impatience_and_Irritability/b225e72158d8f430387f635711725621435a8f7bf864c972beffc684930501a1.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": "b25e057c7a7bfe1ed9303b51bcefd1e7590c73067682c3d6ba58d57c0481e59b", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4923d1b8a16da0659c2da545e5c84dc867b646c819ce783056e2f446dc520d2b", "generation_seconds_batch": 13.195416530943476, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5938694477081299, "target_z": 1.5937498938172496, "ce": 5.601652145385742, "genuineness": 3.8169827461242676, "identity": 0.6766605377197266, "hypothesis": "Las llaves están en la mesa de la cocina. Miren el cajón y luego, junto a la ventana, llévatelas cuando te vayas.", "wer": 0.08695652173913043, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/b25e057c7a7bfe1ed9303b51bcefd1e7590c73067682c3d6ba58d57c0481e59b.mp3" }, { "id": "emo_Impatience_and_Irritability-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-0", "key": "b2eccabb0f4c28db59894b80262a8a90192a5833bc2d096eef652d8037a1bf94", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La puerta sigue abierta.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "ef7f27e869e616d40dbd41edc65af1e62b665e5660524860ef7db57b518b890f", "generation_seconds_batch": 14.016730432980694, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14008614420890808, "target_z": -0.5312500081679039, "ce": 5.4666266441345215, "genuineness": 3.823258876800537, "identity": 0.32445645332336426, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/b2eccabb0f4c28db59894b80262a8a90192a5833bc2d096eef652d8037a1bf94.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": "b314b868006fee8d71da82c5073003d65ff8bf9c91a15cd2bd26bab72a212018", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The road turns left behind the bridge.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e84f390bd4763888a420fab09ae19da129b6be576a27bae531ad3c2b80a14c8d", "generation_seconds_batch": 20.801278779981658, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6735174655914307, "target_z": 3.1718750013613173, "ce": 5.125091552734375, "genuineness": 3.327451705932617, "identity": 0.21158011257648468, "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_Impatience_and_Irritability/b314b868006fee8d71da82c5073003d65ff8bf9c91a15cd2bd26bab72a212018.mp3" }, { "id": "emo_Impatience_and_Irritability-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-0", "key": "b33ac5a070cbb7625f92503f9a8ac94e3f06384979fd09338421ce2a748346b0", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Tür ist noch offen.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "03c321d535289405b0a362e4c31869a129229a442ab8c8ae31913e927fee7e7f", "generation_seconds_batch": 17.479108887026086, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7721077799797058, "target_z": 0.3925781241491767, "ce": 6.125868320465088, "genuineness": 4.507347106933594, "identity": 0.5062247514724731, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/b33ac5a070cbb7625f92503f9a8ac94e3f06384979fd09338421ce2a748346b0.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-1", "key": "b3911dec057e0db8510aa762a85e3ad9a69851a1dbab2eeb5c54010d660f02d6", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "c90106341cd683e1c821c7bbca110032b114340c9c718dd2e106fe3edec8ee0f", "generation_seconds_batch": 13.07682791503612, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4383466243743896, "target_z": 2.8281249986386827, "ce": 5.669164657592773, "genuineness": 3.747946262359619, "identity": 0.41070592403411865, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/b3911dec057e0db8510aa762a85e3ad9a69851a1dbab2eeb5c54010d660f02d6.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-0", "key": "b3d0efe0e2cc9332e69345dd8266ed2f2a2dadf0a1791d85b579355f891472bd", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De deur staat nog open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "495aa1a8afabbf1cb204ab9166762d766f58315c66ac14cc454d42ae7ca9fd55", "generation_seconds_batch": 19.17704564507585, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9712013006210327, "target_z": 0.6835937870958968, "ce": 6.149696350097656, "genuineness": 4.162164688110352, "identity": 0.5013021230697632, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/b3d0efe0e2cc9332e69345dd8266ed2f2a2dadf0a1791d85b579355f891472bd.mp3" }, { "id": "emo_Impatience_and_Irritability-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-1", "key": "b3fcaa33816f9d9f851bd0dcc9413a1642c498bd701ddc2b68d91f02fd38f347", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I found the little box.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "48d01a20654b4a90e0f3ff282922594faf6ee8264a8918928e2d68ab0b1c67df", "generation_seconds_batch": 19.12720317498315, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.046552300453186035, "target_z": -0.6679687394497908, "ce": 6.292664527893066, "genuineness": 4.369274139404297, "identity": 0.47979339957237244, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/b3fcaa33816f9d9f851bd0dcc9413a1642c498bd701ddc2b68d91f02fd38f347.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_Impatience_and_Irritability", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": "828849414acaf46e5597667af37ea6d536073b169edf1e45042167c4e8a995b6", "generation_seconds_batch": 13.245083724032156, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10534501075744629, "target_z": -0.5820312387691322, "ce": 6.300607204437256, "genuineness": 4.1998209953308105, "identity": 0.7232433557510376, "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_Impatience_and_Irritability/b429ad869b4f073af736e4e6510807542fc4f5324b0eb7f096c719d9002f4f71.mp3" }, { "id": "emo_Impatience_and_Irritability-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-1", "key": "b58ed1f0ba9a505c58d1258cef74628e74d9846103e47aa4e6d7b700fd7e18ee", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] He encontrado la cajita.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cf7129834e3f4ae44ca146cd524ce313868bb88d94878ed41c7b707f1aebd7cd", "generation_seconds_batch": 18.300851456006058, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05991426110267639, "target_z": -0.6484375170164665, "ce": 5.80021858215332, "genuineness": 3.936227321624756, "identity": 0.4652629494667053, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/b58ed1f0ba9a505c58d1258cef74628e74d9846103e47aa4e6d7b700fd7e18ee.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": "b5ca0c20da35ac3541c577335dc37bdb04a1793936f5bdcdef0bb23d1311279d", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "23e33decf4470bcfc59f6cf2d340fd7ad19e0f1622b3cc5a9de5b5cd8262b159", "generation_seconds_batch": 18.811890969984233, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0000736713409424, "target_z": 2.1874999618831152, "ce": 5.19657564163208, "genuineness": 3.7040140628814697, "identity": 0.35876598954200745, "hypothesis": "Het gaat linksaf naar de brug, loop verder tot aan het kleine houten hek. Ik wacht aan de andere kant.", "wer": 0.14285714285714285, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/b5ca0c20da35ac3541c577335dc37bdb04a1793936f5bdcdef0bb23d1311279d.mp3" }, { "id": "emo_Impatience_and_Irritability-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-0", "key": "b600f9289aeaf289786b903c2e7743de34aa88af92658a4794589aea8065ce36", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The door is still open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "feec9797f67f3b3eac12ab8d73f0f0cc312902b108673ec4882fe8fb203a9cdc", "generation_seconds_batch": 13.323381691006944, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18952548503875732, "target_z": -0.4589843588343569, "ce": 6.1894097328186035, "genuineness": 3.9927117824554443, "identity": 0.32805901765823364, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/b600f9289aeaf289786b903c2e7743de34aa88af92658a4794589aea8065ce36.mp3" }, { "id": "emo_Impatience_and_Irritability-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-1", "key": "b61ba0f07bc48625c2709b168a79fd3788c6cac73a4b8517ec34834d0e64a79f", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I found the little box.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "4ca7fb88b296f5d70cbc307cd09a522501e3e6c3d885dd913eebd51a5c1829f6", "generation_seconds_batch": 19.5919619029155, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07594865560531616, "target_z": -0.6249999891094615, "ce": 6.149696350097656, "genuineness": 4.143336772918701, "identity": 0.3595724403858185, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/b61ba0f07bc48625c2709b168a79fd3788c6cac73a4b8517ec34834d0e64a79f.mp3" }, { "id": "emo_Impatience_and_Irritability-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-1", "key": "b61bae731d0fcdde10f125acf731a0856cd5eea0a3ee6d6d3e9a77eec2ccb448", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "230380bb9b10925312db812a2180e5cb9d8c83c74215b074b562caa7dea85485", "generation_seconds_batch": 18.758621791028418, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07594865560531616, "target_z": -0.6249999891094615, "ce": 6.149696350097656, "genuineness": 4.406930446624756, "identity": 0.5612384676933289, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/b61bae731d0fcdde10f125acf731a0856cd5eea0a3ee6d6d3e9a77eec2ccb448.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-0", "key": "b6c7ea3af1a449833d779d7bf0c683b4a3115dbda1a4a55ec513b462c8970f74", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De deur staat nog open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "12369f4a39bdf30ee9d8254107d453e3fb3444d999789eafdbb9f14564529e2e", "generation_seconds_batch": 18.064228652976453, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4287049174308777, "target_z": -0.10937498502550956, "ce": 6.125868320465088, "genuineness": 4.243753433227539, "identity": 0.6781550049781799, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/b6c7ea3af1a449833d779d7bf0c683b4a3115dbda1a4a55ec513b462c8970f74.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": "b712ba65cdfd40f956f9e0c002874be3aab7672c2d35d7553bcdc7a4cb1d00e9", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "56cc486af041f68d441265e596cdfa844fe5dc7c62219a28f3fd6695d07e1eea", "generation_seconds_batch": 20.221674534026533, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2411131858825684, "target_z": 1.0781248897332978, "ce": 5.5817952156066895, "genuineness": 3.9173994064331055, "identity": 0.5313639044761658, "hypothesis": "Les clés sont sur la table de la cuisine. J'ai regardé dans le tiroir, puis près de la fenêtre. Prends-les quand tu partiras.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/b712ba65cdfd40f956f9e0c002874be3aab7672c2d35d7553bcdc7a4cb1d00e9.mp3" }, { "id": "emo_Impatience_and_Irritability-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-1", "key": "b7a537c190a627337dbca53c331e5955db0dcdd6cbd798800a14d05a13bac18f", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I found the little box.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "d5765db6cdc54fa0306cd6b7598120d831f5e68241797e3c4b89e0bb76a05f0c", "generation_seconds_batch": 18.679629863006994, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.017155945301055908, "target_z": -0.7109374897901202, "ce": 6.348263263702393, "genuineness": 4.413206577301025, "identity": 0.4235914349555969, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/b7a537c190a627337dbca53c331e5955db0dcdd6cbd798800a14d05a13bac18f.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": "b7ab38b983d79d7eabf8b07def695543672712eb107bc8bf95ba99f75dcab42d", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "5e9257eea0776e0385ea403f8196aa54e65e3ac5de0e65ad58d7058ff40dcfbe", "generation_seconds_batch": 13.270713496953249, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6184450387954712, "target_z": 0.16796878301194482, "ce": 5.744620323181152, "genuineness": 3.9801597595214844, "identity": 0.43365612626075745, "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": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/b7ab38b983d79d7eabf8b07def695543672712eb107bc8bf95ba99f75dcab42d.mp3" }, { "id": "emo_Impatience_and_Irritability-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-0", "key": "b7cbc0d2fcd2e501502a66e80b49109cfb192be05fadba499495683e245d95ae", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Tür ist noch offen.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "5ad2f052bbb31641da6d68d54f533548e97c277c093b076475182bd7139f3fee", "generation_seconds_batch": 13.132569657987915, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5724904537200928, "target_z": 1.5625001470222697, "ce": 5.7406487464904785, "genuineness": 3.898571252822876, "identity": 0.5461665987968445, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist!", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/b7cbc0d2fcd2e501502a66e80b49109cfb192be05fadba499495683e245d95ae.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-0", "key": "b8251953c3ffb93955150ddc4329783719ef1ce1f90c5412eb3e2014e4d2e565", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De deur staat nog open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "817439a47117696e9b40c263e7dc0d6b61f4108a3cbc21b972f8a661a1dc735d", "generation_seconds_batch": 18.064228652976453, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5195663571357727, "target_z": 0.023437484344850906, "ce": 6.0146708488464355, "genuineness": 3.9927117824554443, "identity": 0.7005394697189331, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/b8251953c3ffb93955150ddc4329783719ef1ce1f90c5412eb3e2014e4d2e565.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-1", "key": "b82924fb287f07929259f0b1380b65324ac94fa769c96465f907aadbc1b1fe2a", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "f7871fd4e207f3532212aa47c7c42a529c3cd0da6f2f56c489b269a1e5546819", "generation_seconds_batch": 22.31411813304294, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4313772916793823, "target_z": -0.10546876667613708, "ce": 6.157639026641846, "genuineness": 4.256305694580078, "identity": 0.48799049854278564, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude ramen. 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_Impatience_and_Irritability/b82924fb287f07929259f0b1380b65324ac94fa769c96465f907aadbc1b1fe2a.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-1", "key": "b8322b61d5c2063154a6ca4c78678053ac2a27ea4398eb0e96c92b862c77a27e", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4d97c31ae35b6175eb65b8b45cd843bead8092bd08d322e42c4dbfbfa191d928", "generation_seconds_batch": 12.987187399994582, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18150827288627625, "target_z": -0.47070314456893636, "ce": 5.708878040313721, "genuineness": 4.281409740447998, "identity": 0.5400989055633545, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/b8322b61d5c2063154a6ca4c78678053ac2a27ea4398eb0e96c92b862c77a27e.mp3" }, { "id": "emo_Impatience_and_Irritability-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-0", "key": "b85ca114218ade460101f4d20f9b6007b1a24b803e44a9f75104ceedf3489590", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La puerta sigue abierta.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "474d2d3308c1e29cf0bff9598ac1c60c0dbdb5ee88f9726d4d606a91c0aa309b", "generation_seconds_batch": 18.009480266016908, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3031023144721985, "target_z": -0.2929687285592523, "ce": 5.784333229064941, "genuineness": 4.406930446624756, "identity": 0.721240758895874, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/b85ca114218ade460101f4d20f9b6007b1a24b803e44a9f75104ceedf3489590.mp3" }, { "id": "emo_Impatience_and_Irritability-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-1", "key": "b910fae6f79838675fb432cb6d24e912a925d290e2f01ecd4d11833e01ca56b2", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] He encontrado la cajita.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "db6ee59fc41664cf199f92b0ca2b8564d5c1b4981730776217e7f57bfb7f92e8", "generation_seconds_batch": 18.126249374938197, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.02025759220123291, "target_z": -0.7656249823028749, "ce": 6.0305562019348145, "genuineness": 4.3504462242126465, "identity": 0.5792073011398315, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/b910fae6f79838675fb432cb6d24e912a925d290e2f01ecd4d11833e01ca56b2.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": "b9708c669989003a09d1dafe9e51c413c7ea66f63fb5ae68d0cd83ff559986dd", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "175c69482236678df808566fd9b8f6211fc29487df6cade1ea97fd311bd40300", "generation_seconds_batch": 15.05838883400429, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22025802731513977, "target_z": -0.41406249931934136, "ce": 5.967014789581299, "genuineness": 4.093128204345703, "identity": 0.6207125186920166, "hypothesis": "J'ai cré le numero sur l'enveloppe. Lille and verify the two dernier chiffre. Apple moi quand you're a moment.", "wer": 0.6818181818181818, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/b9708c669989003a09d1dafe9e51c413c7ea66f63fb5ae68d0cd83ff559986dd.mp3" }, { "id": "emo_Impatience_and_Irritability-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-1", "key": "b99e0a5c0bde7b87ca02a9b09683f2035b2a229311a11d676d0fb11b3a029d1f", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] He encontrado la cajita.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "7c84992495a91a2dc6dcf49c49df98bb7d568fdefbef65dbf66d2e0389634a4f", "generation_seconds_batch": 14.38587571901735, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.038535118103027344, "target_z": -0.6796874816222163, "ce": 6.09409761428833, "genuineness": 4.300237655639648, "identity": 0.5783202052116394, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/b99e0a5c0bde7b87ca02a9b09683f2035b2a229311a11d676d0fb11b3a029d1f.mp3" }, { "id": "emo_Impatience_and_Irritability-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-0", "key": "b9c16e46af705164f7e2e9288cbddce756d5f4f6a47b428f579dc974247d8c1b", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The door is still open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b6e86da25a66f90ad60644873331a123ccd33da9b0423cd66f9e12abf5ab8d6e", "generation_seconds_batch": 20.319706824957393, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8001679182052612, "target_z": 0.43359372175266575, "ce": 5.871703147888184, "genuineness": 3.7040140628814697, "identity": 0.408127099275589, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/b9c16e46af705164f7e2e9288cbddce756d5f4f6a47b428f579dc974247d8c1b.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": "ba296bf8502f27af34a5cc6d36c9765b90a8c2de24651027d158300517b1b922", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Someone moved the little blue chair.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "53e5bdafce2f793351a9867ca377aba2088cde5953b4374c6863bfd574ba4580", "generation_seconds_batch": 19.262625991017558, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5743504762649536, "target_z": 0.10351561393929684, "ce": 5.974957466125488, "genuineness": 3.5565271377563477, "identity": 0.2820798456668854, "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": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/ba296bf8502f27af34a5cc6d36c9765b90a8c2de24651027d158300517b1b922.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_Impatience_and_Irritability", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": "dc42188196c2e6eded1929c0161ad937678db6e2a8b06eecfce7bc7a3ec7fce4", "generation_seconds_batch": 13.67164071998559, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.038535118103027344, "target_z": -0.6796874816222163, "ce": 6.022613525390625, "genuineness": 4.557555198669434, "identity": 0.7503319978713989, "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_Impatience_and_Irritability/ba70e7e208a6b15a9236ccd5a69e0e5fd403df2a937202d690effa2cdc45d9f2.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-0", "key": "bba92394e5f811dcb3e275f4cf6e2d23920d20fd717d98352597aeb37c673a8f", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La porte est encore ouverte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "78b2ae5d5ce52a6ab7adb9b5414387fd3d27aeaf979b0624b3391e5e1ef8881e", "generation_seconds_batch": 20.048168768989854, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5823676586151123, "target_z": 0.1152343561117223, "ce": 5.744620323181152, "genuineness": 4.3127899169921875, "identity": 0.5635547041893005, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/bba92394e5f811dcb3e275f4cf6e2d23920d20fd717d98352597aeb37c673a8f.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-0", "key": "bc3f160496f7d1b5ecd232b7418db3191a1b5e9b1ec9eea6ccbc7c14147b1413", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La porte est encore ouverte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "e45caac4874b576a2db8819b03d68602f5b9b32a9f8f6c92b01a02cc899dab29", "generation_seconds_batch": 18.412709088996053, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20956844091415405, "target_z": -0.42968750340329326, "ce": 6.006728172302246, "genuineness": 4.293961524963379, "identity": 0.6378551721572876, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/bc3f160496f7d1b5ecd232b7418db3191a1b5e9b1ec9eea6ccbc7c14147b1413.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-1", "key": "bc4deaf02e5993dd0d175c1f46c45e873b7519bbe6666a1b90ebfa5aa00363bc", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "6add5c9709183c0f1082386b298857218a9099f64825f04260181ab31f1c2b7d", "generation_seconds_batch": 13.11355577094946, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4549049139022827, "target_z": 1.3906249714123364, "ce": 6.0146708488464355, "genuineness": 3.810706615447998, "identity": 0.32536906003952026, "hypothesis": "Ik heb het kleine toosje 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_Impatience_and_Irritability/bc4deaf02e5993dd0d175c1f46c45e873b7519bbe6666a1b90ebfa5aa00363bc.mp3" }, { "id": "emo_Impatience_and_Irritability-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-0", "key": "bc6fe93ce5f46c96d8418abca5685cc1fd5de625fa26023c2326baf0a3e17b19", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Tür ist noch offen.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "6138b46017f7598ce8ddc19e6f56629cfc8852b97e6894b8d5a179483d0ddd49", "generation_seconds_batch": 18.1798039060086, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13474136590957642, "target_z": -0.5390624884288029, "ce": 6.1894097328186035, "genuineness": 4.482243061065674, "identity": 0.46078765392303467, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/bc6fe93ce5f46c96d8418abca5685cc1fd5de625fa26023c2326baf0a3e17b19.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-0", "key": "bce95742854d99d4bc25df2605bca3a44f44151cc644e5ea9777049bc67442df", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La porte est encore ouverte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "9fd177de87bd9afb848864bb6f31a8841c87ec6aec7bc517b0c096c1e5f5ac0a", "generation_seconds_batch": 17.955940387910232, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3111194968223572, "target_z": -0.28124998638682686, "ce": 5.816103935241699, "genuineness": 4.344170093536377, "identity": 0.5274677872657776, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/bce95742854d99d4bc25df2605bca3a44f44151cc644e5ea9777049bc67442df.mp3" }, { "id": "emo_Impatience_and_Irritability-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-0", "key": "bd18e673cfaf48b55917ea96436768e175611b43bb4ddbbd34cb6e01b6ef4938", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La puerta sigue abierta.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "e23212fcaa9bac7c0b17207e4b99f961a4093e30e1f5f2dfe15835c3fbbac828", "generation_seconds_batch": 20.335624507977627, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17081871628761292, "target_z": -0.4863281050907343, "ce": 5.831989288330078, "genuineness": 4.306513786315918, "identity": 0.6661146879196167, "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_Impatience_and_Irritability/bd18e673cfaf48b55917ea96436768e175611b43bb4ddbbd34cb6e01b6ef4938.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": "bd69e4d192e3365e292d52752165024535b364a17b737f2f5d68232a34c3f417", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2f3c31a74316f28e929edb4e8a51bdf504141a095ae4289e5ba71448823d8ac9", "generation_seconds_batch": 15.048688951996155, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.58213210105896, "target_z": 4.500000043562154, "ce": 5.982900142669678, "genuineness": 3.553389072418213, "identity": 0.6071163415908813, "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_Impatience_and_Irritability/bd69e4d192e3365e292d52752165024535b364a17b737f2f5d68232a34c3f417.mp3" }, { "id": "emo_Impatience_and_Irritability-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-0", "key": "bd98e3aec60c76b61bd653f283e339adafa60851a6d5f7aea8c1c8a89cd62e3b", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La puerta sigue abierta.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "2021752fe8eca4f95185f2456c8b4fbcccc014f61d1756f9245816075aa1ae4d", "generation_seconds_batch": 13.114055382087827, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2924126982688904, "target_z": -0.3085937762053583, "ce": 5.903473377227783, "genuineness": 4.362998008728027, "identity": 0.7665995359420776, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/bd98e3aec60c76b61bd653f283e339adafa60851a6d5f7aea8c1c8a89cd62e3b.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-1", "key": "bdffbdc910c7e5f6390f470ffbab3481a0d8752ce1b6bbbf6fb5ae6614d934ea", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "8e56f9cd79a1f2003ca1d62953b6565ca8c5090cef22440ec22f71b63766b704", "generation_seconds_batch": 19.250044613028876, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6312830448150635, "target_z": 1.6484374734543124, "ce": 5.760505676269531, "genuineness": 3.71028995513916, "identity": 0.18417988717556, "hypothesis": "Ik heb een kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/bdffbdc910c7e5f6390f470ffbab3481a0d8752ce1b6bbbf6fb5ae6614d934ea.mp3" }, { "id": "emo_Impatience_and_Irritability-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-0", "key": "be652c1bcb29947c2620934525709146cf04db72651998181ecb11b6cd0f0744", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The door is still open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "10699335d368d576c4f45243a7b1f36355910730b0d2df21358da26121eceea4", "generation_seconds_batch": 13.49553538695909, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5142215490341187, "target_z": 0.015624960521797935, "ce": 6.006728172302246, "genuineness": 3.9676074981689453, "identity": 0.3405236303806305, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/be652c1bcb29947c2620934525709146cf04db72651998181ecb11b6cd0f0744.mp3" }, { "id": "emo_Impatience_and_Irritability-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-1", "key": "beae034f6dd20c0f5b726ee3ccab4a0a58d0a56cd835ff2a90ed1429b51546fc", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] He encontrado la cajita.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "4a7c2e4827ede7985f180e727a105b35f73dcab183ca125f600212f0d28d23b1", "generation_seconds_batch": 17.9396568860393, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21224084496498108, "target_z": -0.42578124149176677, "ce": 6.046441555023193, "genuineness": 4.344170093536377, "identity": 0.5376088619232178, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/beae034f6dd20c0f5b726ee3ccab4a0a58d0a56cd835ff2a90ed1429b51546fc.mp3" }, { "id": "emo_Impatience_and_Irritability-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-1", "key": "befe600d54dc6df268d98d1359b6f92223ed3283429b35864cc105d748220703", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] He encontrado la cajita.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "3d4526f85c04172019f41789f1469c5a98316297c988a6dd38af86c4f991176d", "generation_seconds_batch": 17.981277782004327, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.42603251338005066, "target_z": -0.11328124693703605, "ce": 5.246217727661133, "genuineness": 3.8671910762786865, "identity": 0.6484132409095764, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/befe600d54dc6df268d98d1359b6f92223ed3283429b35864cc105d748220703.mp3" }, { "id": "emo_Impatience_and_Irritability-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-1", "key": "bf00cd2e7f0c14c1d1f9d5a302a1c3db8d29b3ae797b23e99037a927b6acc630", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "e4c4cb926082a4fe1431fc98b3c13dda8c143512ca14480d1078fc0f8b461ccc", "generation_seconds_batch": 18.250473196967505, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06793147325515747, "target_z": -0.6367187312818869, "ce": 6.197352409362793, "genuineness": 4.344170093536377, "identity": 0.6172640323638916, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/bf00cd2e7f0c14c1d1f9d5a302a1c3db8d29b3ae797b23e99037a927b6acc630.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": "bf8602a2bd51819897e45fc2ed2b46b692fb883cf87a2761a10cf236bc02146b", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e11a172a02d96465d60af87332ad9a17e738c0417cdfc9bcfc8a7d34454327b2", "generation_seconds_batch": 13.426427079946734, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.481104850769043, "target_z": 2.8906248407258746, "ce": 5.331601142883301, "genuineness": 3.5220088958740234, "identity": 0.6340015530586243, "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_Impatience_and_Irritability/bf8602a2bd51819897e45fc2ed2b46b692fb883cf87a2761a10cf236bc02146b.mp3" }, { "id": "emo_Impatience_and_Irritability-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-1", "key": "bfc2cc16e4a38659b3fbbb56f9df418d5eec55d398ff3147bc7c9a4068a7adb3", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] He encontrado la cajita.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "6de8da9a193b12211804d66134ec58ed3ec3daf4108e3591fec050013eed7006", "generation_seconds_batch": 19.14660694799386, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4901700019836426, "target_z": -0.01953126599547842, "ce": 5.34748649597168, "genuineness": 4.080576419830322, "identity": 0.4273380935192108, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/bfc2cc16e4a38659b3fbbb56f9df418d5eec55d398ff3147bc7c9a4068a7adb3.mp3" }, { "id": "emo_Impatience_and_Irritability-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-1", "key": "c034974885cc83b0db75cf90952ec04eecd35d6b586bb1bbfddad20b696e1266", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] He encontrado la cajita.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "90c0a1d0a9f572a9911607a3cb1be8300935c92f94293b058e8b53e44bcc4284", "generation_seconds_batch": 17.91355488402769, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13741374015808105, "target_z": -0.5351562700794303, "ce": 5.784333229064941, "genuineness": 4.482243061065674, "identity": 0.5060198307037354, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/c034974885cc83b0db75cf90952ec04eecd35d6b586bb1bbfddad20b696e1266.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-1", "key": "c0b7c86d8883b19c2f7dd72467f091d10ab49928073e48f5df7c206492fd9ad9", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "2a64f2db842d648c7f0abda7a261d10b265b50f38141cc4abb4dc7f82a9657eb", "generation_seconds_batch": 18.035692835925147, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.29775750637054443, "target_z": -0.3007812523823053, "ce": 6.062326908111572, "genuineness": 4.15588903427124, "identity": 0.47773340344429016, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/c0b7c86d8883b19c2f7dd72467f091d10ab49928073e48f5df7c206492fd9ad9.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": "c0b9512451888c57bab2145aa0a054e4c095b39c81c0d1c586cd8d21b5922a46", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bfb831bd5d789ce96610389962e7cf9ca87543e1bef1aea2d14edb20bcfe2cd9", "generation_seconds_batch": 18.731546049006283, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.278002977371216, "target_z": 2.5937501551901736, "ce": 5.645336627960205, "genuineness": 3.660081624984741, "identity": 0.1619277000427246, "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_Impatience_and_Irritability/c0b9512451888c57bab2145aa0a054e4c095b39c81c0d1c586cd8d21b5922a46.mp3" }, { "id": "emo_Impatience_and_Irritability-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-0", "key": "c0dc0e91a705d8cbcf6388dc403e50e675f5f51ca330c1beda30d43cebe4ec58", "bucket": "emo_Impatience_and_Irritability", "phase": "wording", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The door is still open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "fbfc995664750becaed9c2a8ec1240cc26efb92dec5ed74fe10197fe2050f078", "generation_seconds_batch": 14.085063438047655, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11068978905677795, "target_z": -0.5742187585082332, "ce": 6.308549880981445, "genuineness": 4.13078498840332, "identity": 0.2290554940700531, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/c0dc0e91a705d8cbcf6388dc403e50e675f5f51ca330c1beda30d43cebe4ec58.mp3" }, { "id": "emo_Impatience_and_Irritability-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-1", "key": "c14db8ae5137309fb766e3d4e50020f7f0637b19479469c88207b84e9a3e85c5", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] He encontrado la cajita.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "1991af25f6cc1ddb4ed5fe3b15812cb512d1ff02d15ff75d377f3ac7fb6dcc72", "generation_seconds_batch": 17.923133360920474, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10267260670661926, "target_z": -0.5859375006806586, "ce": 5.855817794799805, "genuineness": 4.337893962860107, "identity": 0.5117695927619934, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/c14db8ae5137309fb766e3d4e50020f7f0637b19479469c88207b84e9a3e85c5.mp3" }, { "id": "emo_Impatience_and_Irritability-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-0", "key": "c171645a239e3eaa46d345badbc4c0549a39d02d87f94f7a2aa0f33401aea1cf", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The door is still open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "4ad17232a8f78106a1fa8636cfefe86cb5f57ce5874da24c35310313ceaa12ba", "generation_seconds_batch": 13.054122601053677, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2416372001171112, "target_z": -0.38281249115143745, "ce": 6.23706579208374, "genuineness": 3.8922953605651855, "identity": 0.5879326462745667, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/c171645a239e3eaa46d345badbc4c0549a39d02d87f94f7a2aa0f33401aea1cf.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": "c19ad26bb4a275ce00388e5027afec5e3bcba9dfdc1551aa83232a72bbec2f30", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3ba7e34fb7e72391c96f2095e910fa0800eef8b139292eaff2f60ef21dee99b8", "generation_seconds_batch": 18.900616181083024, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8717987537384033, "target_z": 2.000000087124308, "ce": 6.078212261199951, "genuineness": 3.9173994064331055, "identity": 0.4802335202693939, "hypothesis": "La carretera girá a la izquierda tras el puente. Sigue hasta la pequeña puerta de madera. Te esperaré al otro lado.", "wer": 0.047619047619047616, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/c19ad26bb4a275ce00388e5027afec5e3bcba9dfdc1551aa83232a72bbec2f30.mp3" }, { "id": "emo_Impatience_and_Irritability-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-1", "key": "c1c712f24b2c464707ecca090eaf39167e3ff1ca1e2bca30247ceaeb20f754eb", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I found the little box.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "abed22413e179eb5d3853eac24c2977196c8d2dd78ab4a9142c994cf67b043c5", "generation_seconds_batch": 13.170347981038503, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.004223227500915527, "target_z": -0.7421874979580241, "ce": 6.125868320465088, "genuineness": 3.973883628845215, "identity": 0.5577055811882019, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/c1c712f24b2c464707ecca090eaf39167e3ff1ca1e2bca30247ceaeb20f754eb.mp3" }, { "id": "emo_Impatience_and_Irritability-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-1", "key": "c24cb70b807d420f63764ef9f3a384d6fa789dd6ef183f1e3cef797e57cb8947", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I found the little box.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "c0a7dfcd1403cd1540ec195d29a846788e07637447002d4e619bf212bcb91e38", "generation_seconds_batch": 13.087213178048842, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11870697140693665, "target_z": -0.5625000163358077, "ce": 5.974957466125488, "genuineness": 4.017816066741943, "identity": 0.5330458879470825, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/c24cb70b807d420f63764ef9f3a384d6fa789dd6ef183f1e3cef797e57cb8947.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": "c29c90451b0c9ef0813585d91393a659ff30a636bb2438af9d9845b5e4748b13", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I wrote the number on the envelope.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3ffb6cefe50189d8340cffc023da856838de2660ed52567e3653c3c7f4a3b9c9", "generation_seconds_batch": 13.345635640085675, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3533539772033691, "target_z": 1.242187628644486, "ce": 6.1020402908325195, "genuineness": 3.4341442584991455, "identity": 0.5613813400268555, "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_Impatience_and_Irritability/c29c90451b0c9ef0813585d91393a659ff30a636bb2438af9d9845b5e4748b13.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_Impatience_and_Irritability", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": "1ad9b73db75c5d769ec29b92dc8eb3697dbf78f3e7571202a112da477fc36b18", "generation_seconds_batch": 13.826158610987477, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20155125856399536, "target_z": -0.4414062455757187, "ce": 5.95112943649292, "genuineness": 4.250029563903809, "identity": 0.7085159420967102, "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_Impatience_and_Irritability/c3977db0634952a7f9e4083e6135fbbc87199d34c7cb8c3338515d9ae38c18f4.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-0", "key": "c400f6b348d93f716a1fc0fd34687e7d0ab8c3158c078ed84ff67c2c0975b2a3", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De deur staat nog open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5671811786e2aac5faa23395da1866cf5a7d71c12b9a9d47c99399f2771be150", "generation_seconds_batch": 18.140387666993774, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8482710719108582, "target_z": 0.5039062619115264, "ce": 6.038498878479004, "genuineness": 4.231201171875, "identity": 0.5768709182739258, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/c400f6b348d93f716a1fc0fd34687e7d0ab8c3158c078ed84ff67c2c0975b2a3.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-1", "key": "c426d5d277c7c3e1ba34eae964548007fee49a2da3a31957556b825ea2562c86", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "057cbb82c533ad7c72849a5032b3c00b2951ead0b82c0e2f4fd444364737d2c8", "generation_seconds_batch": 13.508732515969314, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0015508532524108887, "target_z": -0.7382812796086515, "ce": 6.260893821716309, "genuineness": 4.68307638168335, "identity": 0.583937406539917, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/c426d5d277c7c3e1ba34eae964548007fee49a2da3a31957556b825ea2562c86.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": "c47053735c617c05c9e72666c6bb6e51b7acd4de21a0dafcf393ca3b7bb4dcfa", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Escribí el número en el sobre.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d54a4b8ebcfbe9b315da8fe52285ec9e3f4f887d694ac7c2b336aeacd9070529", "generation_seconds_batch": 18.65110465104226, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7266770601272583, "target_z": 0.32617188946399645, "ce": 5.764476776123047, "genuineness": 4.042920112609863, "identity": 0.7071492671966553, "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_Impatience_and_Irritability/c47053735c617c05c9e72666c6bb6e51b7acd4de21a0dafcf393ca3b7bb4dcfa.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_Impatience_and_Irritability", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": "7afee6c7a5e788169b6e46551433a2ad82733183e5c840b47ed836afcc154a68", "generation_seconds_batch": 14.188138357014395, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17482730746269226, "target_z": -0.48046873400452156, "ce": 6.324435234069824, "genuineness": 4.419482707977295, "identity": 0.6957758665084839, "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_Impatience_and_Irritability/c493619abd8899c9b3ce96f2a00a6bcdd900e874ef21436707b986365a8437ee.mp3" }, { "id": "emo_Impatience_and_Irritability-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-1", "key": "c4a9f91d8ca8e62b76aeae372cf6d4bf15e47a24f891656ab8e812ae33c63a66", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I found the little box.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "a1aa5e014a77ea5bed6a94e283a6d6856d181c4018dad5335027fb720d743073", "generation_seconds_batch": 19.942148179979995, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14008614420890808, "target_z": -0.5312500081679039, "ce": 6.23706579208374, "genuineness": 3.923675537109375, "identity": 0.44753384590148926, "hypothesis": "I found the little box. It was beside the old window. We can look inside together", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/c4a9f91d8ca8e62b76aeae372cf6d4bf15e47a24f891656ab8e812ae33c63a66.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-0", "key": "c4ee625c5e87cfebc11bcdb4be086f7b9ff82e330aa7f3a103a75b722865f6a7", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De deur staat nog open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "decfe6935601e20aec1834cc9d8e9d10722799935e563091e45d312806bfa436", "generation_seconds_batch": 17.704139924957417, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.150251865386963, "target_z": 0.9453125946115533, "ce": 5.77639102935791, "genuineness": 3.8295347690582275, "identity": 0.40830308198928833, "hypothesis": "De er staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar, wanneer je klaar bent.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/c4ee625c5e87cfebc11bcdb4be086f7b9ff82e330aa7f3a103a75b722865f6a7.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-0", "key": "c5336b6999b76c1cf452ab81e4b7d6524936417d649555aac4ac017e310f994a", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De deur staat nog open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "3c919a5e5ac8162c99e1a61ca2d21288d88000f59eb3081994a1219209b22cf8", "generation_seconds_batch": 13.055920723942108, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4704153537750244, "target_z": 2.8749999673283844, "ce": 5.895530700683594, "genuineness": 3.785602569580078, "identity": 0.7375847101211548, "hypothesis": "De deur 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_Impatience_and_Irritability/c5336b6999b76c1cf452ab81e4b7d6524936417d649555aac4ac017e310f994a.mp3" }, { "id": "emo_Impatience_and_Irritability-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-1", "key": "c56b444266b0a50f61757186c02ea320264d5e04714319619dbf2d072baf4748", "bucket": "emo_Impatience_and_Irritability", "phase": "wording", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "9955ac06bd99e59771e4b7ca7652065bc0671fe79395d9fa975f90df7df7fe3a", "generation_seconds_batch": 14.662629490951076, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07060384750366211, "target_z": -0.6328125129325145, "ce": 6.316492557525635, "genuineness": 3.9550557136535645, "identity": 0.43965399265289307, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/c56b444266b0a50f61757186c02ea320264d5e04714319619dbf2d072baf4748.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-0", "key": "c5d0eb35a065167a5e61523e9b4d5578cafdbad3a735ec33bc554867cadad956", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De deur staat nog open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "7bdf4f6c9578b0c02aeb00c89f8e859ad6a02a4375636497bf00b5b44d49eebf", "generation_seconds_batch": 19.812315721064806, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5509670376777649, "target_z": 0.0693359637904406, "ce": 6.0305562019348145, "genuineness": 4.18726921081543, "identity": 0.6761763095855713, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/c5d0eb35a065167a5e61523e9b4d5578cafdbad3a735ec33bc554867cadad956.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-0", "key": "c685206872aa8b95f120ade258bbe96788ce680dc64bf3cafb9a979aa6267ee7", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De deur staat nog open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3d6d91e3083dada826d4c5784b4c67118c2392bc8284e7c2a70c5538e657bba6", "generation_seconds_batch": 18.54262054199353, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1074934005737305, "target_z": 0.8828124040271295, "ce": 5.95112943649292, "genuineness": 3.8420867919921875, "identity": 0.5971287488937378, "hypothesis": "De deur staat nog open. Ik heb je ge 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_Impatience_and_Irritability/c685206872aa8b95f120ade258bbe96788ce680dc64bf3cafb9a979aa6267ee7.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": "c69672d6c64e36f434e6a51430dd05cb26e0f36e7e4a62ef11c88477b55c5704", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "46365236e5ce4c1cc0a2342d9c8a528bc46d0f87a7fe479b41c01d9e56c2c6ee", "generation_seconds_batch": 18.900616181083024, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8076612949371338, "target_z": 1.9062501497449045, "ce": 5.8875885009765625, "genuineness": 4.061748504638672, "identity": 0.570290744304657, "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_Impatience_and_Irritability/c69672d6c64e36f434e6a51430dd05cb26e0f36e7e4a62ef11c88477b55c5704.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-1", "key": "c6c37d7a6bb19a2ce81a331f720a0f58d0808af090d808dd2f7daf7d816751fc", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "c53d9e71c81542c885422494e9dd1eaa92cfe468375c09b5fcc663cbd2d9d34e", "generation_seconds_batch": 18.499014214030467, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5511112213134766, "target_z": 1.5312500517300578, "ce": 5.442798614501953, "genuineness": 3.7165660858154297, "identity": 0.5412110686302185, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/c6c37d7a6bb19a2ce81a331f720a0f58d0808af090d808dd2f7daf7d816751fc.mp3" }, { "id": "emo_Impatience_and_Irritability-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-0", "key": "c80d073cf96619d932943701e145ec4c372b7fef4203f6b4b5017351b4fc8f0b", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La puerta sigue abierta.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "d07db5920ce6c8b2b01083346f11a1cff3e0dd8337cde8b504e4248a56edaf55", "generation_seconds_batch": 17.921745307045057, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4113343358039856, "target_z": -0.13476562210720072, "ce": 6.0146708488464355, "genuineness": 4.143336772918701, "identity": 0.3181656002998352, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/c80d073cf96619d932943701e145ec4c372b7fef4203f6b4b5017351b4fc8f0b.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_Impatience_and_Irritability", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": "10f7a6647bfe25739abc5013b1cc9dc5caf2d017080259f22e9fe4e7a4a3afb3", "generation_seconds_batch": 16.42797673807945, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2496543824672699, "target_z": -0.37109374897901204, "ce": 6.213237762451172, "genuineness": 4.293961524963379, "identity": 0.6829265356063843, "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_Impatience_and_Irritability/c82131bfaf89850d394bf3a21117deb94436b65306054c3e1cbac0c65e2f913d.mp3" }, { "id": "emo_Impatience_and_Irritability-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-0", "key": "c84d6efaafad382f1b9b2adc7e15a3852945336be8586dbe5a57ea243ae8d54f", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Tür ist noch offen.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "0b8378994f19c62f3285ec8f7bcf2a02066fb042f60b0b11264b74d51d4a2fb9", "generation_seconds_batch": 18.083581804996356, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6799101233482361, "target_z": 0.257812502041976, "ce": 5.8875885009765625, "genuineness": 4.281409740447998, "identity": 0.5386749505996704, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/c84d6efaafad382f1b9b2adc7e15a3852945336be8586dbe5a57ea243ae8d54f.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_Impatience_and_Irritability", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": "09e51934668938ec08ba2b6359acc4f0dd82cd391e96c4d33d6231b6de6b39fe", "generation_seconds_batch": 14.10972732200753, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07060384750366211, "target_z": -0.6328125129325145, "ce": 6.395919322967529, "genuineness": 4.394378662109375, "identity": 0.41112008690834045, "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_Impatience_and_Irritability/c8907269f81c0a33f09ba3b9d9f76b6acb2a8250e6881dbc11786cea01719e9d.mp3" }, { "id": "emo_Impatience_and_Irritability-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-0", "key": "c8b35ff916724a2374014ba384c54cc7a6a6d2607401291c74195c9b5fcee02b", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The door is still open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "a77a2baa74c49780a5478a8c7816414a947b556ddbb6205a85691c52639aff9a", "generation_seconds_batch": 18.539189837989397, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4741356372833252, "target_z": -0.04296875034032933, "ce": 6.070269584655762, "genuineness": 3.973883628845215, "identity": 0.34462812542915344, "hypothesis": "The 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_Impatience_and_Irritability/c8b35ff916724a2374014ba384c54cc7a6a6d2607401291c74195c9b5fcee02b.mp3" }, { "id": "emo_Impatience_and_Irritability-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-1", "key": "c92f21a7dbf6b6ea6727df1e6f494b4ea99d1716650ef90a55e6a373fb214833", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "3380b59c6ea16dd012ec2abeab1de03dd3b3e66b1ca0354f1c668056ffaff265", "generation_seconds_batch": 20.17597936198581, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10801738500595093, "target_z": -0.5781250204197597, "ce": 5.998785495758057, "genuineness": 4.256305694580078, "identity": 0.5680555701255798, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/c92f21a7dbf6b6ea6727df1e6f494b4ea99d1716650ef90a55e6a373fb214833.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": "c9b4583be0dfa36fdf966f4ad056488787dd38ee13996f59731d084b07d766cb", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Your message arrived after I had left.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d4f9a963be645647361e79a506594997f8b67a139910a4c31fe78b71f7174797", "generation_seconds_batch": 14.079175698920153, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3693883419036865, "target_z": 1.265625112989337, "ce": 5.6413655281066895, "genuineness": 3.528284788131714, "identity": 0.4671729803085327, "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_Impatience_and_Irritability/c9b4583be0dfa36fdf966f4ad056488787dd38ee13996f59731d084b07d766cb.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-0", "key": "ca27dd1e51b45f1e57bdade1b139c7329831faee84c37cc45629ca5c567dcd45", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De deur staat nog open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "0fa250c8425af840d809a207d11dbf29d879fb29a618dcbec56a23a86ffb0f4f", "generation_seconds_batch": 12.991865167976357, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0700799226760864, "target_z": 0.8281249986386827, "ce": 5.959072113037109, "genuineness": 4.068024158477783, "identity": 0.5987321138381958, "hypothesis": "De deur 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_Impatience_and_Irritability/ca27dd1e51b45f1e57bdade1b139c7329831faee84c37cc45629ca5c567dcd45.mp3" }, { "id": "emo_Impatience_and_Irritability-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-1", "key": "ca90761a94020d5c67f692d4b5dd980f7967d27bcf07082b37820ebfdbac434a", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "dc64db57da54f5075523e2f91cd340e453dfefa81515fe8aaebcf4e606b124d8", "generation_seconds_batch": 17.890162783907726, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12137937545776367, "target_z": -0.5585937544242813, "ce": 6.141753673553467, "genuineness": 3.9927117824554443, "identity": 0.4951978325843811, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/ca90761a94020d5c67f692d4b5dd980f7967d27bcf07082b37820ebfdbac434a.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-1", "key": "cae55822b63279cda2b0ea35e1627d549d56f8904c38f88431a0a228f816a1e0", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "a115d21c78bc5f4e482a9c6e0dfb0c22591f057a7f076cee9e74a939209b69b9", "generation_seconds_batch": 19.235095151001588, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1021486520767212, "target_z": 0.8749999673283845, "ce": 5.760505676269531, "genuineness": 3.7542223930358887, "identity": 0.6415379643440247, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/cae55822b63279cda2b0ea35e1627d549d56f8904c38f88431a0a228f816a1e0.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-0", "key": "cb0502bb1bfde9fb9be495deb57a4123af0ce6b56d4d755c42f590a096cfd113", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De deur staat nog open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "0a7ea50aaedeb162723c489675b164ceb1ab12aac949caaefebe7c07ff96df08", "generation_seconds_batch": 18.448496566037647, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.0690319538116455, "target_z": 3.749999847532461, "ce": 5.262103080749512, "genuineness": 3.5596652030944824, "identity": 0.27211931347846985, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/cb0502bb1bfde9fb9be495deb57a4123af0ce6b56d4d755c42f590a096cfd113.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": "cb0fffe5ecb425ba28aedd10d9671a504dd9abad92c192211033b50d3640da8e", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The keys are on the kitchen table.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c0de914632e909a960a84988d21d791c93af7cbd43efa27bff1ef5ab3df2ba39", "generation_seconds_batch": 15.842690689023584, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.643832802772522, "target_z": 0.20507816226606143, "ce": 5.959072113037109, "genuineness": 3.8169827461242676, "identity": 0.20358502864837646, "hypothesis": "Keys are on the kitchen table. I checked the drawer, then looked beside the window. Take them with you when you leave.", "wer": 0.043478260869565216, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/cb0fffe5ecb425ba28aedd10d9671a504dd9abad92c192211033b50d3640da8e.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-1", "key": "cb17f41da0120b8dfc40fdb5c019904e6f2f98e14188a77ae00c6186f2b07f9a", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "1db95c724ff39ccad1a7fc254358fe239a9bf0672b3cb32ab7399b41a172395d", "generation_seconds_batch": 17.920167751028202, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10801738500595093, "target_z": -0.5781250204197597, "ce": 6.062326908111572, "genuineness": 4.444586753845215, "identity": 0.6519378423690796, "hypothesis": "J'ai trouvé la 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_Impatience_and_Irritability/cb17f41da0120b8dfc40fdb5c019904e6f2f98e14188a77ae00c6186f2b07f9a.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": "ccdb813114ca7aa45e539d0a21370a60aa63dd2107b6a8d6a41fd0763cd4aa72", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9af4b66c5ac7a2e3514f66a0ec9b36f715e9e089033ed21c7e4ddf08c7f0f081", "generation_seconds_batch": 13.690077606006525, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.77559232711792, "target_z": 1.8593748325579706, "ce": 6.252951145172119, "genuineness": 3.9801597595214844, "identity": 0.6559025049209595, "hypothesis": "Ton message est arrivé après mon départ. Je l'ai relu. Puis j'ai rongé mon téléphone. Dis-moi quand nous pourrons parler.", "wer": 0.047619047619047616, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/ccdb813114ca7aa45e539d0a21370a60aa63dd2107b6a8d6a41fd0763cd4aa72.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": "cce286b7747a59da1b7492e96742b5a9d89ebd133c6b64e1f96e78c963b9d425", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0e8d274ed387b741b6d2cdb6f1b00e413e5e1a45bbe94715b3d3660f9e1781ce", "generation_seconds_batch": 16.653743503033184, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7055861949920654, "target_z": 3.218749970051019, "ce": 5.605623245239258, "genuineness": 3.6192874908447266, "identity": 0.35860562324523926, "hypothesis": "Pfff, sleutels! Legen op de keukentafel. Ik keek in de en daarna naast het raam. Neem ze mee als je weggaat.", "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_Impatience_and_Irritability/cce286b7747a59da1b7492e96742b5a9d89ebd133c6b64e1f96e78c963b9d425.mp3" }, { "id": "emo_Impatience_and_Irritability-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-0", "key": "ccfb113bebb24225bbd3dc9631d296bac82c12bfa50d1f6a39a6fc994ed1c70f", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The door is still open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "005bed8a4aa6ef45b7351393c6dd31353f197b7925563dd943712a86452af024", "generation_seconds_batch": 18.091762345982715, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19353407621383667, "target_z": -0.4531249877481442, "ce": 6.197352409362793, "genuineness": 4.306513786315918, "identity": 0.316758930683136, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/ccfb113bebb24225bbd3dc9631d296bac82c12bfa50d1f6a39a6fc994ed1c70f.mp3" }, { "id": "emo_Impatience_and_Irritability-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-0", "key": "cd8cc8b8591f84c51aa0716bcb328e0ec3a3f176b4e68a0002452868ecc3269b", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Tür ist noch offen.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "4ec63c2719d02c1f1380b5199b4943d93e6cb0e9ed5a51d4e342768e5f28b972", "generation_seconds_batch": 18.041134004946798, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5083527565002441, "target_z": 1.4687498611456342, "ce": 6.141753673553467, "genuineness": 4.545003414154053, "identity": 0.6412515044212341, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/cd8cc8b8591f84c51aa0716bcb328e0ec3a3f176b4e68a0002452868ecc3269b.mp3" }, { "id": "emo_Impatience_and_Irritability-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-1", "key": "cdd8b9270e9698d8d19cb604cdc4bd116cbc208615778585173cdf756aede081", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] He encontrado la cajita.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "45911c04e3c3bf85bba30022e80121e83cbd72953903b97ce6538a560aae7702", "generation_seconds_batch": 17.949045690940693, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06525906920433044, "target_z": -0.6406249931934135, "ce": 5.990842819213867, "genuineness": 4.595211505889893, "identity": 0.639615535736084, "hypothesis": "He conduel he encontrado 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_Impatience_and_Irritability/cdd8b9270e9698d8d19cb604cdc4bd116cbc208615778585173cdf756aede081.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": "ce9ed4ae72a1b76be5b4b7c8ba65662878f6592d2a63b42b2a1eac900eb38697", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "beae041632981826329e887e2dd201733f45177d353bb79523d79f21f23d681e", "generation_seconds_batch": 13.315782825928181, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.278002977371216, "target_z": 2.5937501551901736, "ce": 5.677107334136963, "genuineness": 3.9676074981689453, "identity": 0.791735827922821, "hypothesis": "Oh ! La route tourne à gauche après le pont. Continue jusqu'à la petite barrière en bois. Je te tendrai de l'autre côté.", "wer": 0.15, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/ce9ed4ae72a1b76be5b4b7c8ba65662878f6592d2a63b42b2a1eac900eb38697.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": "cec1d6f117ce8501fab36be38a8d0e128ac48b569425799828430cf8f11bc180", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "5630e9b60016a836195e460fb436837cdc12524d1d1a96edca4cbba9fa168fe4", "generation_seconds_batch": 14.292289865086786, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4704153537750244, "target_z": 2.8749999673283844, "ce": 5.6532793045043945, "genuineness": 3.8169827461242676, "identity": 0.6438355445861816, "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": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/cec1d6f117ce8501fab36be38a8d0e128ac48b569425799828430cf8f11bc180.mp3" }, { "id": "emo_Impatience_and_Irritability-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-0", "key": "cee173ba8669662c93d13b65bd89d00b78963daefb8ab6b6b4897fed7b96bbd7", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Tür ist noch offen.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "83b070c9c43c533ce4cbe803f40ad97c162f8d2605f3ae1ac1823119607871a1", "generation_seconds_batch": 18.952459497959353, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.475236177444458, "target_z": 4.343749915598327, "ce": 5.605623245239258, "genuineness": 4.030367851257324, "identity": 0.33916735649108887, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/cee173ba8669662c93d13b65bd89d00b78963daefb8ab6b6b4897fed7b96bbd7.mp3" }, { "id": "emo_Impatience_and_Irritability-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-0", "key": "cee4fd71436640ccda25e459a90c8bfbcabd625109b1aa126052a74ce794eca6", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The door is still open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "b9324c9184423178802340563f3a402583e8e0b51b99822f88dda4103141b3db", "generation_seconds_batch": 20.319706824957393, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.42469632625579834, "target_z": -0.1152343561117223, "ce": 6.340320587158203, "genuineness": 3.9299514293670654, "identity": 0.1646553874015808, "hypothesis": "The door is still open. Put your coat on the chair. Tell me when you are ready.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/cee4fd71436640ccda25e459a90c8bfbcabd625109b1aa126052a74ce794eca6.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": "cf153aa76bd0581c643de815321ced4dc1eab4937d283311bdcd693416f4a759", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "50c4ed399219a4a3466e142ed278d6aa44328a99ee5339c2a9eb77b2273373ed", "generation_seconds_batch": 13.156847144011408, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.7531652450561523, "target_z": 4.749999760408153, "ce": 5.669164657592773, "genuineness": 3.528284788131714, "identity": 0.6368969678878784, "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_Impatience_and_Irritability/cf153aa76bd0581c643de815321ced4dc1eab4937d283311bdcd693416f4a759.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-1", "key": "cf2cc0a1eb07479767cf671c5e97573edcafd751c8a95ff43868dbc150b9a0c6", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "088361ddca6089b5cef285dde375417f911a95f0f5e671cafa81cb7baaa9c6b4", "generation_seconds_batch": 14.08595608198084, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.278002977371216, "target_z": 2.5937501551901736, "ce": 5.138991355895996, "genuineness": 3.6789097785949707, "identity": 0.7010725736618042, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/cf2cc0a1eb07479767cf671c5e97573edcafd751c8a95ff43868dbc150b9a0c6.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_Impatience_and_Irritability", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": "f4382d815312062963be4bb5619722ca3f3d0e30e6de18679e4ac8aadf6016c2", "generation_seconds_batch": 13.419965266017243, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11068978905677795, "target_z": -0.5742187585082332, "ce": 6.308549880981445, "genuineness": 4.570107460021973, "identity": 0.5440673828125, "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_Impatience_and_Irritability/cf68e6506caaaad7e7371e72de9d5417fef89211300487ff83acd2484eaab510.mp3" }, { "id": "emo_Impatience_and_Irritability-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-0", "key": "cf98dde33122bccdd63b8a593a01216c0b4e782e51330481ae8a088bb175b1bf", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The door is still open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "928aa1a724cf07908b3f46a264f0de7571598c08ab9ce1e8c92d434e9561c8fe", "generation_seconds_batch": 17.956502715009265, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.39930856227874756, "target_z": -0.1523437353658389, "ce": 6.149696350097656, "genuineness": 4.105680465698242, "identity": 0.30184483528137207, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/cf98dde33122bccdd63b8a593a01216c0b4e782e51330481ae8a088bb175b1bf.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": "d018eedba19e4b2ddd1c2fea131ee9930f469910dad0afdef8282ed984e8e474", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "097f8ece49f506c9059cea4a0ad74e6a0f829728661f0ae3cf0f40e728bbadc9", "generation_seconds_batch": 13.866928608971648, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.459725856781006, "target_z": 2.8593750939308946, "ce": 5.081407070159912, "genuineness": 3.5941832065582275, "identity": 0.47884851694107056, "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_Impatience_and_Irritability/d018eedba19e4b2ddd1c2fea131ee9930f469910dad0afdef8282ed984e8e474.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-0", "key": "d038bac16fbf7e9675c0fd16c2ddda6ed31b0b65dedef11178d4b1969fbccee2", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La porte est encore ouverte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "abcef04a0eebf75b1790a25ee1521a0a144b1f393f650b473a7dfbd6840ee9e4", "generation_seconds_batch": 20.85946439707186, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5131735801696777, "target_z": 2.937499809415576, "ce": 5.49045467376709, "genuineness": 3.6412534713745117, "identity": 0.46894311904907227, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/d038bac16fbf7e9675c0fd16c2ddda6ed31b0b65dedef11178d4b1969fbccee2.mp3" }, { "id": "emo_Impatience_and_Irritability-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-0", "key": "d07b029581e2e705d5abfc515a186c45976d0e84aabce11c428cb9b7954758c4", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The door is still open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "f0c4576f9798875372304c122ac00ee48a2a6105486f93f897457713eb011ad6", "generation_seconds_batch": 20.940930979908444, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0973278284072876, "target_z": -0.5937499809415576, "ce": 6.1020402908325195, "genuineness": 3.7793264389038086, "identity": 0.4253745377063751, "hypothesis": "The 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_Impatience_and_Irritability/d07b029581e2e705d5abfc515a186c45976d0e84aabce11c428cb9b7954758c4.mp3" }, { "id": "emo_Impatience_and_Irritability-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-1", "key": "d09da37c9a0fe4b1111441635d2e831d4d3cd78ffc0448632ca7b1c21d2fbd42", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] He encontrado la cajita.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "c69fe43bf0143fe5039bde0b033c8281de611aa5838a73c9018e2318b5441701", "generation_seconds_batch": 20.558270503999665, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0469815731048584, "target_z": -0.8046875142938318, "ce": 6.213237762451172, "genuineness": 4.7081804275512695, "identity": 0.5332096219062805, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/d09da37c9a0fe4b1111441635d2e831d4d3cd78ffc0448632ca7b1c21d2fbd42.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_Impatience_and_Irritability", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3628e9db22346d565a12e632cf60ac560e19447d3ad9a0f369f86c99f1922798", "generation_seconds_batch": 13.723297380958684, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09198302030563354, "target_z": -0.6015625047646106, "ce": 6.372091293334961, "genuineness": 4.099404335021973, "identity": 0.08421365916728973, "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_Impatience_and_Irritability/d11caac31fa3732e2517803823f1b039213fb31e9438619fd83d8b232c894b7d.mp3" }, { "id": "emo_Impatience_and_Irritability-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-0", "key": "d12ca059f22c6fe59b82034dfc9135196d8d4386f95f7191e4cb91e5a5c45489", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La puerta sigue abierta.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "b91e414ad8e70f8f2433c9208818f04438050e1ad688a5622b20e21d7da4e3bf", "generation_seconds_batch": 18.43369045702275, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17215490341186523, "target_z": -0.48437499591604805, "ce": 5.903473377227783, "genuineness": 4.030367851257324, "identity": 0.6708264350891113, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/d12ca059f22c6fe59b82034dfc9135196d8d4386f95f7191e4cb91e5a5c45489.mp3" }, { "id": "emo_Impatience_and_Irritability-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-0", "key": "d167c0b9dc0e9292f96751a84e27cd4ac4887032a4022f4c179c5ec720aa19dc", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La puerta sigue abierta.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "31a78e762e2238daed958fee8f868e6656fd2643a9cca4583271c5e326d69810", "generation_seconds_batch": 13.037632800056599, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22693902254104614, "target_z": -0.4042968663216021, "ce": 5.669164657592773, "genuineness": 4.18099308013916, "identity": 0.6007744073867798, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/d167c0b9dc0e9292f96751a84e27cd4ac4887032a4022f4c179c5ec720aa19dc.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": "d1875c2dd4bc4a26c109eb9b3a9467688d5ad1256e3ba82333959541f9098cd9", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "d8831a4959057590d32dcda9930692f0769517cfa9d192bd85d736c3d6e8ad9c", "generation_seconds_batch": 18.904618831002153, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.4324779510498047, "target_z": 4.281250073511135, "ce": 5.542081832885742, "genuineness": 3.550251007080078, "identity": 0.5706799626350403, "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_Impatience_and_Irritability/d1875c2dd4bc4a26c109eb9b3a9467688d5ad1256e3ba82333959541f9098cd9.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-1", "key": "d1cbf312dd9dfff3f91b029d0b5d0f156267724c619b810d1263aa7ff9c40eb9", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "fccaa87d58efc48b37de0d6dadc1552af0f08f387a35cd729ffdf00141927941", "generation_seconds_batch": 13.035405406029895, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.027845531702041626, "target_z": -0.6953124857061682, "ce": 6.1894097328186035, "genuineness": 4.432034492492676, "identity": 0.6735751628875732, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/d1cbf312dd9dfff3f91b029d0b5d0f156267724c619b810d1263aa7ff9c40eb9.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_Impatience_and_Irritability", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": "52c1c0fa8b180c00ffa1f40deb3713e6e6174cb7f7685598cfd31becff6ad9d8", "generation_seconds_batch": 13.732400184962898, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11336219310760498, "target_z": -0.5703124965967067, "ce": 6.2767791748046875, "genuineness": 4.507347106933594, "identity": 0.7313389778137207, "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_Impatience_and_Irritability/d2319f0ba4d4a13f099c61fd2524d2cd47bb09bca092815ed8a29e7f5b0c527c.mp3" }, { "id": "emo_Impatience_and_Irritability-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-0", "key": "d3567c88c3747ef55e6af37ff3a5b3bbff74e6fc383464d230ff6855da8cfc8c", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The door is still open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "b3cfb6acd0276e2afdee241f53820ef6d951ac50e98d3176e90bda8d699579be", "generation_seconds_batch": 13.054122601053677, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.48883381485939026, "target_z": -0.021484375170164664, "ce": 5.974957466125488, "genuineness": 3.8671910762786865, "identity": 0.45903682708740234, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/d3567c88c3747ef55e6af37ff3a5b3bbff74e6fc383464d230ff6855da8cfc8c.mp3" }, { "id": "emo_Impatience_and_Irritability-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-0", "key": "d367b19df8c9b77763a13bc442bcf3b15be7d96e5b0c9f71ced61bf194751451", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Tür ist noch offen.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "81133ea77b5a59faa77d4556e679a7de118ecf2ff4c2d0fbfa789371a478f65e", "generation_seconds_batch": 17.70584717905149, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4014570713043213, "target_z": 1.3125000816790386, "ce": 5.974957466125488, "genuineness": 4.055472373962402, "identity": 0.44901448488235474, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/d367b19df8c9b77763a13bc442bcf3b15be7d96e5b0c9f71ced61bf194751451.mp3" }, { "id": "emo_Impatience_and_Irritability-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-1", "key": "d376cf71ea7a78db650f6aec1f079deb0b21964609d9b1e070eeaf6d7a6077e7", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I found the little box.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "836a2638f76f85eb778a423dc66d3de953cc6069ce7a9431e073176435e07866", "generation_seconds_batch": 17.86286833998747, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0469815731048584, "target_z": -0.8046875142938318, "ce": 6.078212261199951, "genuineness": 4.369274139404297, "identity": 0.40360650420188904, "hypothesis": "I found the little box. It was beside the old window. We can look inside together", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/d376cf71ea7a78db650f6aec1f079deb0b21964609d9b1e070eeaf6d7a6077e7.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_Impatience_and_Irritability", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": "7b02457c7305acfabffbfb0b2f4cf6e73de94627e38aeb06080bbad45012f9c5", "generation_seconds_batch": 17.617465610965155, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.038535118103027344, "target_z": -0.6796874816222163, "ce": 6.054384231567383, "genuineness": 4.482243061065674, "identity": 0.7784144282341003, "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_Impatience_and_Irritability/d3fab0ead1fc9dcf899f59bddb0c9d4b54373ba1829b6dc49f77fc4027ce1740.mp3" }, { "id": "emo_Impatience_and_Irritability-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-0", "key": "d4829512ad172d033550d628a85b60f737bed1ea320900ac8e7a4851e25f2562", "bucket": "emo_Impatience_and_Irritability", "phase": "wording", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Tür ist noch offen.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "c84861cc6e5dfd16d9b58595dace34f351671fe81df856327da2f07090fe7fb2", "generation_seconds_batch": 14.320809809025377, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20155125856399536, "target_z": -0.4414062455757187, "ce": 6.308549880981445, "genuineness": 4.607763767242432, "identity": 0.7619024515151978, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/d4829512ad172d033550d628a85b60f737bed1ea320900ac8e7a4851e25f2562.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-0", "key": "d497522d54c3bb35cc382619c5188537d3cc9ef98ca96052fca4d5dc9e4e045b", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La porte est encore ouverte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "219faed55a01aa80a68bc2e5de243d6aef86b4d67ba7ab0b718ee0ccbbefc8cb", "generation_seconds_batch": 13.232800244935788, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1769757270812988, "target_z": 0.984374952353894, "ce": 5.990842819213867, "genuineness": 4.306513786315918, "identity": 0.5361716747283936, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/d497522d54c3bb35cc382619c5188537d3cc9ef98ca96052fca4d5dc9e4e045b.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": "d4e2e860d07524f9b69d33306916902624c14165123007024976f93f5a9f0b81", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3d62a3ef00b34e0f5d23cda7c8ef4e277d6687f3a72e3800bf789d4ce95c247d", "generation_seconds_batch": 13.262265203986317, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6605352163314819, "target_z": 0.22949213585502445, "ce": 5.839932441711426, "genuineness": 4.15588903427124, "identity": 0.3552517890930176, "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_Impatience_and_Irritability/d4e2e860d07524f9b69d33306916902624c14165123007024976f93f5a9f0b81.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": "d51cb23ebda07612f9f8a955ddf15edec40731010dbb43d45aeb878036a218a2", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bbe491045bc886c09608a084d51a9aff3290bd7e743207064f804b30b2f41113", "generation_seconds_batch": 13.315782825928181, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7969715595245361, "target_z": 1.8906249278501823, "ce": 5.95112943649292, "genuineness": 4.231201171875, "identity": 0.6322533488273621, "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_Impatience_and_Irritability/d51cb23ebda07612f9f8a955ddf15edec40731010dbb43d45aeb878036a218a2.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-0", "key": "d530af5c1885d33f1f0777c138b17ddf798fc0130e2123c637f34b57f54f5cc1", "bucket": "emo_Impatience_and_Irritability", "phase": "wording", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De deur staat nog open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "75f58926344336345d4302cb123caf27feebe09dfc981a0964fb8c38c2dee0dd", "generation_seconds_batch": 14.2863726610085, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6852549314498901, "target_z": 0.26562502586502895, "ce": 6.062326908111572, "genuineness": 4.369274139404297, "identity": 0.6786882877349854, "hypothesis": "De deur 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_Impatience_and_Irritability/d530af5c1885d33f1f0777c138b17ddf798fc0130e2123c637f34b57f54f5cc1.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-1", "key": "d5758779e4ff3b7fc76fb5773b079bc3d29711d2c881ae07627388079c815975", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "37fe7f211bddd712520542e3fef553baa7109614ae51d0341c1dbcc38b37178a", "generation_seconds_batch": 18.733814411098137, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18818926811218262, "target_z": -0.46093751157119717, "ce": 6.221180438995361, "genuineness": 4.369274139404297, "identity": 0.6389107704162598, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/d5758779e4ff3b7fc76fb5773b079bc3d29711d2c881ae07627388079c815975.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": "d59473b549464f378ca6f35f71638d33e8b139d466d40cc1921d4c5330f896aa", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1b6d95b49cd3b2757f8b2337c99a80dfeb2d3306d5361f96c2cebe2e76d82758", "generation_seconds_batch": 21.65155936498195, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.299381971359253, "target_z": 2.6249999019851535, "ce": 5.597680568695068, "genuineness": 3.747946262359619, "identity": 0.3777593672275543, "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_Impatience_and_Irritability/d59473b549464f378ca6f35f71638d33e8b139d466d40cc1921d4c5330f896aa.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-0", "key": "d64591e22bffc678e0d9faece342c9312f4a6130130f96f42e95afdb5f8d615d", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La porte est encore ouverte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "e1b827416e86e03f4e069a91c5b9730b0f64049190fa6fff85c477b120b197e5", "generation_seconds_batch": 18.47156018705573, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20823225378990173, "target_z": -0.43164061257797953, "ce": 5.998785495758057, "genuineness": 4.532451152801514, "identity": 0.5658868551254272, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/d64591e22bffc678e0d9faece342c9312f4a6130130f96f42e95afdb5f8d615d.mp3" }, { "id": "emo_Impatience_and_Irritability-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-1", "key": "d6c3b79fff781f4ed3e23bfe0f8c1d5fcc343ea03da47e6892d218a8eba1c8c5", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "68d61cb1a0b08adc4b16516939666b408dd444555d290860772634bb76c8ba0b", "generation_seconds_batch": 17.875798788038082, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08396583795547485, "target_z": -0.613281246937036, "ce": 6.324435234069824, "genuineness": 3.9048471450805664, "identity": 0.2461118847131729, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/d6c3b79fff781f4ed3e23bfe0f8c1d5fcc343ea03da47e6892d218a8eba1c8c5.mp3" }, { "id": "emo_Impatience_and_Irritability-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-1", "key": "d7358c8cd6837055a2bb7ffeeec93751b653a0a6a50ae8bc70ebc66af6ba4669", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "21ba39f1703059a1e5281455e719c219c767103f1335f86dfef11231a32480f7", "generation_seconds_batch": 18.758621791028418, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06258666515350342, "target_z": -0.6445312551049399, "ce": 6.340320587158203, "genuineness": 4.2249250411987305, "identity": 0.5091513395309448, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/d7358c8cd6837055a2bb7ffeeec93751b653a0a6a50ae8bc70ebc66af6ba4669.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": "d739ad8e47a6fc80720bcd5237f946b15e8761e699269484eea48b84640fa142", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fe29223e04ce4371a21bbc0d49c1d0a44b2a71baed21ff725dc92379912d5d6c", "generation_seconds_batch": 20.05405311100185, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4727994501590729, "target_z": -0.044921859515015566, "ce": 5.387199878692627, "genuineness": 3.9173994064331055, "identity": 0.54831862449646, "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_Impatience_and_Irritability/d739ad8e47a6fc80720bcd5237f946b15e8761e699269484eea48b84640fa142.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-0", "key": "d790f3ca230fe7c2fccd4e9a13d38b8574ba4f17a283d0615cd4a692b88dc9a9", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La porte est encore ouverte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "4561daa5fd7f9676767f476835d1b94d6de32422ed79ceea1d85605cc479ec6b", "generation_seconds_batch": 17.644325688946992, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2197340726852417, "target_z": 1.0468749686897019, "ce": 5.7128496170043945, "genuineness": 3.9676074981689453, "identity": 0.6949954032897949, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/d790f3ca230fe7c2fccd4e9a13d38b8574ba4f17a283d0615cd4a692b88dc9a9.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": "d7cef732a585a7e39d0d2ebde1c63c1d119f07c12d088cb3e61e2daeb7b7432f", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "51fb589f535b90abc1db2dd14920509a4ce3cd116e30a43fb3f2a861ee1fc30a", "generation_seconds_batch": 18.811890969984233, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5618007183074951, "target_z": 1.5468749251275478, "ce": 5.649308204650879, "genuineness": 3.6789097785949707, "identity": 0.34620600938796997, "hypothesis": "De bed gaat linksaf naar de brug. Loop verder. Tot aan het kleine houten hek. Ik wacht aan de andere kant.", "wer": 0.09523809523809523, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/d7cef732a585a7e39d0d2ebde1c63c1d119f07c12d088cb3e61e2daeb7b7432f.mp3" }, { "id": "emo_Impatience_and_Irritability-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-0", "key": "d84180480aa4e4f0c78ff3241fd62115c58dd712c23f8178f7e075b154734e9f", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La puerta sigue abierta.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "25f8187c8921a8ab8f697069e280669d31ac394c4e93077ccebf2afd683686c4", "generation_seconds_batch": 18.470272303093225, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.1973071098327637, "target_z": 3.9375000707885004, "ce": 5.8875885009765625, "genuineness": 3.672633647918701, "identity": 0.5324140787124634, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/d84180480aa4e4f0c78ff3241fd62115c58dd712c23f8178f7e075b154734e9f.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-0", "key": "d869dea46dee1aa41d5a23fe644a144a45d5633b2a86902a824545cb802e8976", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La porte est encore ouverte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "4d639b51e5336acea6e59e367fb87bffce04ff0730bebd576004fc94aa96b6a1", "generation_seconds_batch": 19.042664563981816, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1962064504623413, "target_z": -0.4492187693987717, "ce": 6.1020402908325195, "genuineness": 4.168440818786621, "identity": 0.7569020986557007, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/d869dea46dee1aa41d5a23fe644a144a45d5633b2a86902a824545cb802e8976.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-1", "key": "d93bcbf8ae4ae6110e8c23c1ea66a5a011dc6b471caca52efb4d9a1191ba4452", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "79da2b3703bc7042bb6bcae8c5d8b8e79e630a3f099683ed86666bb40d251863", "generation_seconds_batch": 17.903178279986605, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1048210859298706, "target_z": 0.878906272802065, "ce": 6.09409761428833, "genuineness": 3.9048471450805664, "identity": 0.38558173179626465, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/d93bcbf8ae4ae6110e8c23c1ea66a5a011dc6b471caca52efb4d9a1191ba4452.mp3" }, { "id": "emo_Impatience_and_Irritability-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-0", "key": "d944301000d18b94fc3d8e8318ab75e24893e0f7cbbadf9166e3716e6ce180f0", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The door is still open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "acaf195f49eff12ca3c709d09b6a1741f0d219d95165cefbd839f968d1d415f0", "generation_seconds_batch": 13.42370345001109, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4928424060344696, "target_z": -0.015625004083951937, "ce": 6.109982967376709, "genuineness": 3.911123275756836, "identity": 0.4822075366973877, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/d944301000d18b94fc3d8e8318ab75e24893e0f7cbbadf9166e3716e6ce180f0.mp3" }, { "id": "emo_Impatience_and_Irritability-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-0", "key": "d9aeb8a98dfcc531cf342b674cf293adc816a9b718f346c4225afbd897803b14", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La puerta sigue abierta.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "605aeedf7640c158930dab8edb709d4611230f3d63dbcb2728c7f503f7c8d3cf", "generation_seconds_batch": 13.455581575981341, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10801738500595093, "target_z": -0.5781250204197597, "ce": 5.871703147888184, "genuineness": 4.068024158477783, "identity": 0.6515228152275085, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/d9aeb8a98dfcc531cf342b674cf293adc816a9b718f346c4225afbd897803b14.mp3" }, { "id": "emo_Impatience_and_Irritability-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-0", "key": "d9ddb5ff77fcf5dfa5864f770bad307f37a812a5fa89ca7ea2affeb28a075623", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The door is still open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "808d30173ed05f21b0a4cebbf63e665d56093f474014bb3992666e04a2192e36", "generation_seconds_batch": 18.091762345982715, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14543095231056213, "target_z": -0.5234374843448509, "ce": 6.109982967376709, "genuineness": 4.055472373962402, "identity": 0.42435282468795776, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/d9ddb5ff77fcf5dfa5864f770bad307f37a812a5fa89ca7ea2affeb28a075623.mp3" }, { "id": "emo_Impatience_and_Irritability-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-0", "key": "db048aecfcc8f35cf09462bb7b4b8f66ae29c8a0ec41f6604b1db9dc9d8522d7", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Tür ist noch offen.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "7058eeabfd6d984395124d5f985bdd50692e368701f260706835ddb5b01134c7", "generation_seconds_batch": 17.70584717905149, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5885248184204102, "target_z": 1.5859376313671207, "ce": 5.871703147888184, "genuineness": 4.293961524963379, "identity": 0.3741539716720581, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/db048aecfcc8f35cf09462bb7b4b8f66ae29c8a0ec41f6604b1db9dc9d8522d7.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_Impatience_and_Irritability", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": "1dc3b24fcba016602fe8cb407f0ca00056fcf13994c4074f05b47ebaca1f70be", "generation_seconds_batch": 13.74647383892443, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09465542435646057, "target_z": -0.5976562428530842, "ce": 6.348263263702393, "genuineness": 4.105680465698242, "identity": 0.3222665786743164, "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_Impatience_and_Irritability/db192910e9ae67de251fb2a990940eab881f66f627c78b50b638ce61f5a63679.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": "db2a59b6dc5edf096440b1d658a428d4d8f48d0603237cdfbfcf7a00a2fa936c", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Escribí el número en el sobre.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c2ed402871d935f03a67e14e15f07876097dd1ff3871a23dedc7594bb44e3c7a", "generation_seconds_batch": 15.555460990057327, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9685288667678833, "target_z": 0.6796874816222163, "ce": 6.086154937744141, "genuineness": 3.9425034523010254, "identity": 0.6467361450195312, "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_Impatience_and_Irritability/db2a59b6dc5edf096440b1d658a428d4d8f48d0603237cdfbfcf7a00a2fa936c.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-0", "key": "db89f1c738e719f87bf3c56f48170a8dcc4f1888587143175a2ba0ccd5544818", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De deur staat nog open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "a1aab9196c2ddafe8cb5db1a15585bf1259a8542c7957c202edea528bd6d1028", "generation_seconds_batch": 17.704139924957417, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9252467155456543, "target_z": 2.0781251511062218, "ce": 5.935244083404541, "genuineness": 3.8546390533447266, "identity": 0.6473884582519531, "hypothesis": "De deur 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_Impatience_and_Irritability/db89f1c738e719f87bf3c56f48170a8dcc4f1888587143175a2ba0ccd5544818.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-1", "key": "dc4d6a41873dadb46b9de9deab180b1d0407b9a26bddf8d6b7ca2b22b7ab996f", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "de83ed5ab9ba4f603b5b89683031d52a9d37f53114fd6d512d18449a4993bb66", "generation_seconds_batch": 18.344065628014505, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.012240409851074219, "target_z": -0.7539062401304495, "ce": 6.181467056274414, "genuineness": 4.432034492492676, "identity": 0.6976774334907532, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/dc4d6a41873dadb46b9de9deab180b1d0407b9a26bddf8d6b7ca2b22b7ab996f.mp3" }, { "id": "emo_Impatience_and_Irritability-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-1", "key": "dcabccad29209795a5feb9e5898d84a970d82388af68719bbab7d7fe817cae10", "bucket": "emo_Impatience_and_Irritability", "phase": "wording", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] He encontrado la cajita.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "ae1676ac4d1e4a3c7e1de8748eda924da358f119e6ec7cda4554adcda56c2cea", "generation_seconds_batch": 13.581446272903122, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0469815731048584, "target_z": -0.8046875142938318, "ce": 6.157639026641846, "genuineness": 4.6203155517578125, "identity": 0.6523038744926453, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/dcabccad29209795a5feb9e5898d84a970d82388af68719bbab7d7fe817cae10.mp3" }, { "id": "emo_Impatience_and_Irritability-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-1", "key": "dd62402819dce6a8ab0cc3db587c0d8a76bd0b5e98e8d835dd75fb33aef0953a", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I found the little box.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "21096c2f94af245054334e302be7ffc1d0e581471cf78bc976c087ef7f25df46", "generation_seconds_batch": 18.02963152900338, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24430960416793823, "target_z": -0.37890622923991096, "ce": 5.808161735534668, "genuineness": 3.6349775791168213, "identity": 0.45859917998313904, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/dd62402819dce6a8ab0cc3db587c0d8a76bd0b5e98e8d835dd75fb33aef0953a.mp3" }, { "id": "emo_Impatience_and_Irritability-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-0", "key": "dd7ed94c1ef517010d3e4bebe533d5a19544d3f55e1c57316de0b1ad6e912ab5", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La puerta sigue abierta.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "36a5f6a14b3ee3d409594c39b770d6eaf78597c86debad3aee23a4ec9b9a2bd7", "generation_seconds_batch": 18.915850221994333, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18818926811218262, "target_z": -0.46093751157119717, "ce": 5.847874641418457, "genuineness": 4.080576419830322, "identity": 0.6038472652435303, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/dd7ed94c1ef517010d3e4bebe533d5a19544d3f55e1c57316de0b1ad6e912ab5.mp3" }, { "id": "emo_Impatience_and_Irritability-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-0", "key": "dd85aea14432b22ac9e55bf088deae2a978ecd9b6cea99f0851bb3fcc3dcfb54", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The door is still open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "ac465959ebbcd4c0a27a2dd6979a3836838147b8e9cecd7fbb571ff822d0c858", "generation_seconds_batch": 17.82554499001708, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5831799507141113, "target_z": 1.5781250204197597, "ce": 5.450741291046143, "genuineness": 3.3588318824768066, "identity": 0.5399112701416016, "hypothesis": "The 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_Impatience_and_Irritability/dd85aea14432b22ac9e55bf088deae2a978ecd9b6cea99f0851bb3fcc3dcfb54.mp3" }, { "id": "emo_Impatience_and_Irritability-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-1", "key": "de62a2247e15b8c414876783bf27703e279212129295cbc1b0b4e2407e45b330", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] He encontrado la cajita.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "d550192e1594d9715c55991eba97c0f577f1c5dba68152ce7442ab6705a23ca7", "generation_seconds_batch": 17.837154263979755, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18952548503875732, "target_z": -0.4589843588343569, "ce": 6.109982967376709, "genuineness": 4.017816066741943, "identity": 0.527982234954834, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana. ¡Prieja! 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_Impatience_and_Irritability/de62a2247e15b8c414876783bf27703e279212129295cbc1b0b4e2407e45b330.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-0", "key": "de712c6bdd7169f7c6d54a3b8f1b99c8960984907462a5d32b920826eaef18fb", "bucket": "emo_Impatience_and_Irritability", "phase": "wording", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La porte est encore ouverte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "c9b0e6ece629e10dc82d2cee526e0556e850fe4fb596b1ffad4653662f540440", "generation_seconds_batch": 14.074501736089587, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3218090534210205, "target_z": -0.26562502586502895, "ce": 5.990842819213867, "genuineness": 4.457139015197754, "identity": 0.7150750160217285, "hypothesis": "La porte est c'est éteint et car j'ai encore un voy d'air. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.4444444444444444, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/de712c6bdd7169f7c6d54a3b8f1b99c8960984907462a5d32b920826eaef18fb.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-0", "key": "deabfc027d33c20854129def2db11c363a9f304c86b36078ed610ab87eabc009", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De deur staat nog open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "191c698e1653a1778aab9ba3c96bde28f1c3f9b04dadfbc048f13f0a7a6a4431", "generation_seconds_batch": 18.140387666993774, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.36991220712661743, "target_z": -0.19531248570616822, "ce": 6.1020402908325195, "genuineness": 4.268857479095459, "identity": 0.6971263885498047, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/deabfc027d33c20854129def2db11c363a9f304c86b36078ed610ab87eabc009.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-1", "key": "dec5464bd57b7a38a75f3745baf955303260b00008bb5530532d765c7a09e1e8", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "36e5161d877b1239393df222704b4db2394f960b6d9c7de752aff6bc0c61f578", "generation_seconds_batch": 18.92247041501105, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1283485889434814, "target_z": 2.3749998366419227, "ce": 5.982900142669678, "genuineness": 3.7165660858154297, "identity": 0.4613998234272003, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/dec5464bd57b7a38a75f3745baf955303260b00008bb5530532d765c7a09e1e8.mp3" }, { "id": "emo_Impatience_and_Irritability-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-1", "key": "df53a13e2530625b91bd31004aa99c9321d29a5efc56d6796f48979fb1af0277", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I found the little box.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "cf32542c1264a85f25806a4ad5ba2548b2367263e57d8153eb99b2c039ac8efe", "generation_seconds_batch": 19.001721453969367, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0011215806007385254, "target_z": -0.7343749741349711, "ce": 6.284721851348877, "genuineness": 4.494794845581055, "identity": 0.42712169885635376, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/df53a13e2530625b91bd31004aa99c9321d29a5efc56d6796f48979fb1af0277.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": "e1e199137ca3cecc88f511c414c3d6631e5f18cccac5195fab8c847728ae8859", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "016c75ad8d583bcc92243c139dc544333b4c1ed45b9bc9093aa48092fd8e294f", "generation_seconds_batch": 14.155993068008684, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.326629877090454, "target_z": 1.2031249224049132, "ce": 5.303802013397217, "genuineness": 3.6287014484405518, "identity": 0.2449401617050171, "hypothesis": "De weg gaat linksaf naar de brug. Loop verder. Tot aan het kleine houten hek. 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_Impatience_and_Irritability/e1e199137ca3cecc88f511c414c3d6631e5f18cccac5195fab8c847728ae8859.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": "e2106e66469325389af07df27079e9f983a761bd60320ed5b9f2f40e75e9eb47", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Someone moved the little blue chair.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "297c40efc149cd9291de057cbdabd06594a5f3f48b1c00ce1d3bedfb7cb4328d", "generation_seconds_batch": 13.28623522107955, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.31646427512168884, "target_z": -0.27343750612592793, "ce": 5.756534099578857, "genuineness": 3.5345609188079834, "identity": 0.23485243320465088, "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_Impatience_and_Irritability/e2106e66469325389af07df27079e9f983a761bd60320ed5b9f2f40e75e9eb47.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-0", "key": "e253e9b9b0dd7e3a5867c1f720f7b32db16b667c54a5bf773cd49cba50133b6b", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La porte est encore ouverte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "a6669d4e6868ac5194968f21f901709c73c1e9e2acfc44f7c1d94717c8fc509e", "generation_seconds_batch": 13.232800244935788, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8309004902839661, "target_z": 0.47851562482983534, "ce": 5.752562999725342, "genuineness": 4.017816066741943, "identity": 0.4609305262565613, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/e253e9b9b0dd7e3a5867c1f720f7b32db16b667c54a5bf773cd49cba50133b6b.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-1", "key": "e2972035443006fe419f3e9d5ee1cc42506dca9a39f768bd2f1eb56fdedf76d4", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "545a1e98b4822cf075f777b87f6499482eb65591b43d7914f26ff91d17e6a248", "generation_seconds_batch": 18.37529989297036, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4281809329986572, "target_z": 1.3515624394213797, "ce": 6.1020402908325195, "genuineness": 3.9173994064331055, "identity": 0.35478249192237854, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen het er samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/e2972035443006fe419f3e9d5ee1cc42506dca9a39f768bd2f1eb56fdedf76d4.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-1", "key": "e2d7f9950c1aebeae311457bf0cdca936d0928a4fb527d2a8f9a6e62d17818d9", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "b40f7573c8f55ea9c9b0eb478fee29a45a597d8df42aa1b85f56320ed943b62e", "generation_seconds_batch": 14.08595608198084, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9284429550170898, "target_z": 0.621093770760089, "ce": 5.689021587371826, "genuineness": 4.268857479095459, "identity": 0.43083053827285767, "hypothesis": "J'ai trouvé la 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_Impatience_and_Irritability/e2d7f9950c1aebeae311457bf0cdca936d0928a4fb527d2a8f9a6e62d17818d9.mp3" }, { "id": "emo_Impatience_and_Irritability-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-0", "key": "e3515a70c9e567df7c89ac60c0962272cb3f01702663ba9ec50c1ee97049adea", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La puerta sigue abierta.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "27c7405ac9649e8ec8ffa4827c8dcd70bcebc0f4c2e4384d3a0c04460754354d", "generation_seconds_batch": 18.192877508932725, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.27370595932006836, "target_z": -0.33593747889958164, "ce": 5.95112943649292, "genuineness": 4.306513786315918, "identity": 0.5673966407775879, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/e3515a70c9e567df7c89ac60c0962272cb3f01702663ba9ec50c1ee97049adea.mp3" }, { "id": "emo_Impatience_and_Irritability-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-0", "key": "e3bf00d2114a4d89cd9ccfd19780ee0dc7036211737f1b862830fc08a467bc89", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Tür ist noch offen.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "5eda428d7e6ca519e50b9dd5f1582540302ac2e927822712feacbe28e368868d", "generation_seconds_batch": 18.1798039060086, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6010744571685791, "target_z": 0.14257814593025367, "ce": 6.213237762451172, "genuineness": 4.570107460021973, "identity": 0.6502841711044312, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/e3bf00d2114a4d89cd9ccfd19780ee0dc7036211737f1b862830fc08a467bc89.mp3" }, { "id": "emo_Impatience_and_Irritability-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-1", "key": "e3ec9bcaa60bab7170f60cd51e3e19ce311045f943d854b066eaab1117f09ae8", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I found the little box.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "9e70e6abdf7d9547316f6016975789e6d6ae0da1cc5a78014cc8633d4e303da9", "generation_seconds_batch": 18.831526429974474, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.004223227500915527, "target_z": -0.7421874979580241, "ce": 6.372091293334961, "genuineness": 4.432034492492676, "identity": 0.32853055000305176, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/e3ec9bcaa60bab7170f60cd51e3e19ce311045f943d854b066eaab1117f09ae8.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": "e3eef0cbe37549cd837ee2777fa0c0e332e4612e6718f6e41e60e17783ad87d4", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Someone moved the little blue chair.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1a08fe53d5d2219767bc681bd131dc278e45d28e33ce622a6cfe6ab058c2fffd", "generation_seconds_batch": 13.862638226011768, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5369369387626648, "target_z": 0.048828121426542054, "ce": 6.23706579208374, "genuineness": 4.168440818786621, "identity": 0.49608901143074036, "hypothesis": "Someone moved the little blue chair. Used to stand here, beside the tall bookshelf. We can put it back after lunch.", "wer": 0.045454545454545456, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/e3eef0cbe37549cd837ee2777fa0c0e332e4612e6718f6e41e60e17783ad87d4.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-1", "key": "e3fb6359a6f029fb8adab12546099fe1c0b9f45d5cfc4740e43c902f9e0fc2e0", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "d0761856e66cd88343d2ebda67aba91b11459b82a99041178121040aa628bb5e", "generation_seconds_batch": 24.223658098024316, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1240517795085907, "target_z": -0.5546874925127547, "ce": 6.117925643920898, "genuineness": 4.6203155517578125, "identity": 0.7015402317047119, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/e3fb6359a6f029fb8adab12546099fe1c0b9f45d5cfc4740e43c902f9e0fc2e0.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": "e4219bcbde5a3ecea25351eeb832647c0fa977818e520c06e248569957b191ef", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Someone moved the little blue chair.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e760b4c5daa44a237507501ce41f938d6598ff13694c9f742ef956127bd0156b", "generation_seconds_batch": 19.262625991017558, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8349090814590454, "target_z": 0.48437499591604805, "ce": 5.637393951416016, "genuineness": 3.6663577556610107, "identity": 0.2875889539718628, "hypothesis": "Someone moved the little blue chair. It used to stand here beside the tall bookshelf. You can put it back after lunch.", "wer": 0.045454545454545456, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/e4219bcbde5a3ecea25351eeb832647c0fa977818e520c06e248569957b191ef.mp3" }, { "id": "emo_Impatience_and_Irritability-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-1", "key": "e4c50c4b96e7fb948839f183b60f96244808a4c7b79279f840a136a3a7959ba7", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I found the little box.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "c7f378c9af8bfe814eb11b02f2e95482dcc06f1853c853e71d4222a3626b4303", "generation_seconds_batch": 12.991034857928753, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0011215806007385254, "target_z": -0.7343749741349711, "ce": 6.38797664642334, "genuineness": 4.337893962860107, "identity": 0.5144436359405518, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/e4c50c4b96e7fb948839f183b60f96244808a4c7b79279f840a136a3a7959ba7.mp3" }, { "id": "emo_Impatience_and_Irritability-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-1", "key": "e4d93acc51c80d136059956777a25e1ea6e8f9ddfa78ac607b8abd0da88154a4", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] He encontrado la cajita.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "510a3b9cc1020cd5fb018043c2cbafc4063597e3409074c6d4e746ab4bfa09a4", "generation_seconds_batch": 13.477240241016261, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05991426110267639, "target_z": -0.6484375170164665, "ce": 6.062326908111572, "genuineness": 4.7081804275512695, "identity": 0.594368577003479, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/e4d93acc51c80d136059956777a25e1ea6e8f9ddfa78ac607b8abd0da88154a4.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-0", "key": "e4e689f0f4f8001600b5254fdb145aeb6786cd3be88d84fd2a6b7f8677a81d9b", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De deur staat nog open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "2fe703f10ed52852eabcdb8a630897cd08d342430ce31b1b8f3d44472ede7604", "generation_seconds_batch": 15.053585440968163, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.158268928527832, "target_z": 0.9570311625353627, "ce": 6.213237762451172, "genuineness": 4.068024158477783, "identity": 0.6827094554901123, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/e4e689f0f4f8001600b5254fdb145aeb6786cd3be88d84fd2a6b7f8677a81d9b.mp3" }, { "id": "emo_Impatience_and_Irritability-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-0", "key": "e52c7318e27e73e337923806f91a9eda7b8d9e812c14924dba5cf9bd5cb825cd", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Tür ist noch offen.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "bee3b081982d39af91fd4fb4984fad0c4bee63440dee6d06d03206bf5407bd4e", "generation_seconds_batch": 18.891891437000595, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7266770601272583, "target_z": 0.32617188946399645, "ce": 6.221180438995361, "genuineness": 4.457139015197754, "identity": 0.5024137496948242, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/e52c7318e27e73e337923806f91a9eda7b8d9e812c14924dba5cf9bd5cb825cd.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": "e5a35e1693f2c244d95e0ee1a04d57ed8a73c5309189257fc51df3cb0641fc65", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6f805c0180cc8878dd8d1ad1ff1b222406cde97156d6c4cfc50451e19d63d593", "generation_seconds_batch": 13.238258647965267, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.085590362548828, "target_z": 2.312499994554731, "ce": 5.426913261413574, "genuineness": 3.6349775791168213, "identity": 0.2997731566429138, "hypothesis": "Jemand hat den kleinen blauen Stuhl umgestellt. Er stand hier neben dem hohen Bücherregal. Wir stellen nie nach dem Essen zurück.", "wer": 0.047619047619047616, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/e5a35e1693f2c244d95e0ee1a04d57ed8a73c5309189257fc51df3cb0641fc65.mp3" }, { "id": "emo_Impatience_and_Irritability-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-0", "key": "e5caa74216fc246298486755621bf5f29d4c277c1ea16b0299bd7cde8160846a", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Tür ist noch offen.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "bf3525a6999a377f3b979a42a6df17c965dbb48bc2b5c337bac2a7e405385d73", "generation_seconds_batch": 23.132250800030306, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14810332655906677, "target_z": -0.5195312659954784, "ce": 6.284721851348877, "genuineness": 4.7081804275512695, "identity": 0.36742323637008667, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/e5caa74216fc246298486755621bf5f29d4c277c1ea16b0299bd7cde8160846a.mp3" }, { "id": "emo_Impatience_and_Irritability-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-0", "key": "e6ed2a3799a0d0165c2a9735e70ff9e3f4695cb804b70a2d180b0de23f36d2de", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La puerta sigue abierta.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "445a72d262f45a2a438376e959f632baac25dcfa75b7c28c7b5b67c6fb24f0d5", "generation_seconds_batch": 14.016730432980694, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1240517795085907, "target_z": -0.5546874925127547, "ce": 5.5738525390625, "genuineness": 3.9801597595214844, "identity": 0.5402379035949707, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/e6ed2a3799a0d0165c2a9735e70ff9e3f4695cb804b70a2d180b0de23f36d2de.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_Impatience_and_Irritability", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": "ff450e3d3995e6db51ed78ad978ad06854f21efa2ce75d0c57e866f51b286968", "generation_seconds_batch": 14.10972732200753, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.038535118103027344, "target_z": -0.6796874816222163, "ce": 6.419747352600098, "genuineness": 4.243753433227539, "identity": 0.4258381128311157, "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_Impatience_and_Irritability/e6f1e80cc6606ef00fdc322d5829b94fd65ad80a74ab015f88321e5dc194804c.mp3" }, { "id": "emo_Impatience_and_Irritability-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-0", "key": "e6fd7331867d3651fa0e7ba1fd789231f1d218e4fc19c19fb7283de1ea46bfa7", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La puerta sigue abierta.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "9503fa9d0fd3ee373c3b785980c890e4d8399aa34ad03da930b37788c7fec7cd", "generation_seconds_batch": 13.074674005038105, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8669778108596802, "target_z": 0.5312499646057499, "ce": 5.0476508140563965, "genuineness": 3.8169827461242676, "identity": 0.6614433526992798, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/e6fd7331867d3651fa0e7ba1fd789231f1d218e4fc19c19fb7283de1ea46bfa7.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": "e71c87241dcda7348fc91e514b50f68d7f17383594ee85ece51106136709f142", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The road turns left behind the bridge.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7d891d1992f3436339d4f179d0072cf9dec76a1720c5dcf201e1876af3ed36a3", "generation_seconds_batch": 14.331522535998374, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4976632595062256, "target_z": 1.4531249877481442, "ce": 6.054384231567383, "genuineness": 3.4247303009033203, "identity": 0.29152438044548035, "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_Impatience_and_Irritability/e71c87241dcda7348fc91e514b50f68d7f17383594ee85ece51106136709f142.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-1", "key": "e7246a356a56eb9703efae99bfc99df7ad04761dc73909c4ac040741bff1aefc", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 1.0, "cfg": 1.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "5d9edf4680c96d0848c9311bd3c4c70d240f0757ac7ffef039eaef5618312981", "generation_seconds_batch": 18.30818030098453, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3752569854259491, "target_z": -0.18750000544526926, "ce": 5.824047088623047, "genuineness": 4.143336772918701, "identity": 0.6092908382415771, "hypothesis": "Ik 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_Impatience_and_Irritability/e7246a356a56eb9703efae99bfc99df7ad04761dc73909c4ac040741bff1aefc.mp3" }, { "id": "emo_Impatience_and_Irritability-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-1", "key": "e76f9694fab0fa2f0104c46cbee3e6036821086e26e4c66209eed478eb465fe1", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "49b8540fe252340b0a455017df97712eb4f46fccdafe6be9fef53d4fb78305d2", "generation_seconds_batch": 17.568160369992256, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11870697140693665, "target_z": -0.5625000163358077, "ce": 6.149696350097656, "genuineness": 4.118232727050781, "identity": 0.2568948268890381, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/e76f9694fab0fa2f0104c46cbee3e6036821086e26e4c66209eed478eb465fe1.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-1", "key": "e78c642aa16a6d0b74063ef406e83f8ecb4077d156d9561bddd562006a86119e", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "aaf9168ab21d3555e22b8e00fb8a61ea6e8d10e10920b376e3c830bee4cfb1a4", "generation_seconds_batch": 20.14855235198047, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.150251865386963, "target_z": 0.9453125946115533, "ce": 5.1926045417785645, "genuineness": 3.8797430992126465, "identity": 0.6915830373764038, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/e78c642aa16a6d0b74063ef406e83f8ecb4077d156d9561bddd562006a86119e.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": "e86bedadc3e756a8a4ff94192d065a897e123ec85407f486b2e8fec81d1aa6cd", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I wrote the number on the envelope.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1da2faf8c24ca4f7dcbedb90e22fb821ae029f1b08dac0bc4fd5b9e11cf4da91", "generation_seconds_batch": 13.803051889990456, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1395621299743652, "target_z": 0.9296873727168313, "ce": 5.903473377227783, "genuineness": 3.390212059020996, "identity": 0.2865961790084839, "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_Impatience_and_Irritability/e86bedadc3e756a8a4ff94192d065a897e123ec85407f486b2e8fec81d1aa6cd.mp3" }, { "id": "emo_Impatience_and_Irritability-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-0", "key": "e8bfbb1e3f0a30fb8ca362b9205f95677f6ee14e71729df1f653a8d556e1d58a", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La puerta sigue abierta.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "d7ce47fa1f95d49419d4c180ef1375505f1abf299f1b783a6e725d6965881db5", "generation_seconds_batch": 18.189138951012865, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9621362686157227, "target_z": 3.593750068065866, "ce": 5.661221981048584, "genuineness": 3.6192874908447266, "identity": 0.625691294670105, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/e8bfbb1e3f0a30fb8ca362b9205f95677f6ee14e71729df1f653a8d556e1d58a.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-1", "key": "e8ca8c170701d9627d4b4b46e8103df914ccd1959543e7b97e758c5538668ed7", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "67ed66278edf4782bf5dd0fe13a6b3f23c5ae87fcae4b6159037e813a567c2ed", "generation_seconds_batch": 18.523337046965025, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0749008655548096, "target_z": 2.2968751211572407, "ce": 5.561938762664795, "genuineness": 3.8546390533447266, "identity": 0.5555033683776855, "hypothesis": "Et j'ai trouvé la petite boîte ! Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.05263157894736842, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/e8ca8c170701d9627d4b4b46e8103df914ccd1959543e7b97e758c5538668ed7.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-1", "key": "e8d5e1a2027be8edaa3d2eda15676b1c2d5b8c900210062878acda4ed69d23cf", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "b56db062656668ccc3e51ec890b0d89314207ed0d32e4d1084b86c6fef858de1", "generation_seconds_batch": 17.93838132591918, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5569798946380615, "target_z": 0.07812497685760568, "ce": 6.133810997009277, "genuineness": 4.13078498840332, "identity": 0.5368480086326599, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/e8d5e1a2027be8edaa3d2eda15676b1c2d5b8c900210062878acda4ed69d23cf.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": "e91e09135abdb44de28906af540025f86b9d729283eb0e1eaf8da8330e4d161f", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I wrote the number on the envelope.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "44411e33e7f812adacf31c086a147857ce9d88c79eba98f13f42753355e70fa8", "generation_seconds_batch": 18.294561796006747, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1342175006866455, "target_z": 0.9218751102667023, "ce": 5.927301406860352, "genuineness": 3.653805732727051, "identity": 0.2997724413871765, "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_Impatience_and_Irritability/e91e09135abdb44de28906af540025f86b9d729283eb0e1eaf8da8330e4d161f.mp3" }, { "id": "emo_Impatience_and_Irritability-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-0", "key": "e95d8849c616878715ca5dc4e2e30fdb4a1f89167f102ba067ab3de19a0bb244", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La puerta sigue abierta.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "2033d91e139d3653ed39d400d401f00120a28b0dc1e129aa43ac541d02c44280", "generation_seconds_batch": 18.43369045702275, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2496543824672699, "target_z": -0.37109374897901204, "ce": 5.935244083404541, "genuineness": 4.344170093536377, "identity": 0.6051135659217834, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/e95d8849c616878715ca5dc4e2e30fdb4a1f89167f102ba067ab3de19a0bb244.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": "e9cb537588f2af772245b0c6847b08a5cfbf438de8a9feae4832d6f552503907", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "05021c12d510d279ae3b917007e3b9f62d70c31056a4ff4d8ce9e3a1fca244ad", "generation_seconds_batch": 13.866928608971648, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8552403450012207, "target_z": 3.4374999401020383, "ce": 5.911416053771973, "genuineness": 4.005263805389404, "identity": 0.5527260303497314, "hypothesis": "Ich kam als schon weg war. Ich las sie zweimal, dann legte ich das Handy weg. Sag mir, wann wir reden können.", "wer": 0.125, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/e9cb537588f2af772245b0c6847b08a5cfbf438de8a9feae4832d6f552503907.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_Impatience_and_Irritability", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": "b584f4b4bffb3fbe4a3e0b530dcd5c28927401fde364c5d4523bf1c8b2426d8e", "generation_seconds_batch": 13.419965266017243, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11336219310760498, "target_z": -0.5703124965967067, "ce": 6.3641486167907715, "genuineness": 4.469690799713135, "identity": 0.5540979504585266, "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_Impatience_and_Irritability/e9d266c3907611a53d0c5f7688a7e231bba29ead6f87b8ae8d29cb37ab2fae41.mp3" }, { "id": "emo_Impatience_and_Irritability-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-1", "key": "e9d3ee9667393c4b4ef8e713f8b911154537473f8b7881f36e0243b47c906870", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "5cf4394f6998a3951c72c3e2f052151c9305097dc9acaba511505966e4f5ab77", "generation_seconds_batch": 18.128538768040016, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.26168015599250793, "target_z": -0.3535156357203738, "ce": 6.109982967376709, "genuineness": 4.21237325668335, "identity": 0.5682770013809204, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/e9d3ee9667393c4b4ef8e713f8b911154537473f8b7881f36e0243b47c906870.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": "ea0ec05edf5a8c58722a26c4a6a6338b5a9baa38f25719ec38c0a91d200d8afc", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "5e5c298d5a2f8efe0626c3d9d07dde9aa22587d6ff3dc822160633ebcbe24954", "generation_seconds_batch": 18.37734621495474, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.716275691986084, "target_z": 3.234374843448509, "ce": 5.474569320678711, "genuineness": 3.264691114425659, "identity": 0.6530149579048157, "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_Impatience_and_Irritability/ea0ec05edf5a8c58722a26c4a6a6338b5a9baa38f25719ec38c0a91d200d8afc.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": "ea74fdb23ea151240e9a5f099fa1eab4bf88b090ba60a1805f1e1d7218462c0c", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "265e1601deda95e595a2c9ee4bb0400325773782eb49655e94b395cde058e95e", "generation_seconds_batch": 18.41066536400467, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.475236177444458, "target_z": 4.343749915598327, "ce": 5.649308204650879, "genuineness": 3.440420389175415, "identity": 0.42598479986190796, "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_Impatience_and_Irritability/ea74fdb23ea151240e9a5f099fa1eab4bf88b090ba60a1805f1e1d7218462c0c.mp3" }, { "id": "emo_Impatience_and_Irritability-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-1", "key": "eafc051a8cdba79cd06228a7779351c068eb33e938c66850edec80d222e57be4", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] He encontrado la cajita.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e7d1f0ee3a7c2d36e49aa902f1a0c9505f73c2cc3b28e8056f7d59427412d8e5", "generation_seconds_batch": 13.31577121396549, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3017660975456238, "target_z": -0.2949218812960926, "ce": 5.514282703399658, "genuineness": 4.20609712600708, "identity": 0.652239978313446, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/eafc051a8cdba79cd06228a7779351c068eb33e938c66850edec80d222e57be4.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-0", "key": "eb598b70950eb5253e399257fa29f3745b7562f8397af4b24dfe27275b8d8186", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De deur staat nog open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "745376934a32d933fdf68669375edc9c72d639b68508304f836afc76f638d955", "generation_seconds_batch": 20.351500272052363, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9621362686157227, "target_z": 3.593750068065866, "ce": 5.403085231781006, "genuineness": 3.7542223930358887, "identity": 0.06545908749103546, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/eb598b70950eb5253e399257fa29f3745b7562f8397af4b24dfe27275b8d8186.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_Impatience_and_Irritability", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": "294ede72f58b02e4b4ad7fc863cdf36819acce3b28e837d44af2eb32d94e8199", "generation_seconds_batch": 13.28518233099021, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1507757306098938, "target_z": -0.515625004083952, "ce": 6.24500846862793, "genuineness": 4.432034492492676, "identity": 0.8566511869430542, "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_Impatience_and_Irritability/ebe89981a89e9506d02bacdfa583f9bfe1f04faa699193749ab6419de85c588f.mp3" }, { "id": "emo_Impatience_and_Irritability-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-0", "key": "ec07cdb27483056182e2f648d610dbd74cda4811ae02ca6347dd358da68f1da0", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Tür ist noch offen.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "52366f6049cff947b8bbf6809d31aaf56e825ecbd30076ffbc8f6a97faf9277b", "generation_seconds_batch": 20.065921458997764, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.3255820274353027, "target_z": 4.124999945547308, "ce": 6.141753673553467, "genuineness": 3.8169827461242676, "identity": 0.3239400386810303, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/ec07cdb27483056182e2f648d610dbd74cda4811ae02ca6347dd358da68f1da0.mp3" }, { "id": "emo_Impatience_and_Irritability-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-0", "key": "ed1787d276e996acc1f0055a0d8dc503817fedff1afa45759600d0086faa8e86", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Tür ist noch offen.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "2d301141e5d4bbfe2e464a0ad3825afe5e5a694380fdf3cf4458635920555377", "generation_seconds_batch": 14.02990688092541, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0994763374328613, "target_z": 0.87109383610332, "ce": 5.911416053771973, "genuineness": 4.457139015197754, "identity": 0.508299708366394, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/ed1787d276e996acc1f0055a0d8dc503817fedff1afa45759600d0086faa8e86.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": "ed4145ac47d8ec0244ac8de56ada3edd9ac11edf49cfdc02795ca991f2a98b6f", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "946994eed6e76d65ac97de2d454781488e10d02e30076d7e9cf9c8ded96aaf0d", "generation_seconds_batch": 13.343703162972815, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.406277894973755, "target_z": 2.781250029948981, "ce": 5.7406487464904785, "genuineness": 3.7291181087493896, "identity": 0.2908266484737396, "hypothesis": "Jemand hat den kleinen blauen Stuhl umgestellt. Er stammt her. Neben dem hohen Bücherregal. Wir stellen ihn nach dem Essen zurück.", "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_Impatience_and_Irritability/ed4145ac47d8ec0244ac8de56ada3edd9ac11edf49cfdc02795ca991f2a98b6f.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-1", "key": "ed632c3dd4ee792a643b11bca037f8a34f2c1502ac688a1b232f69f040b7d136", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "5186700697bbae181b728fb17cdcd45134a229a89ee38e318ed49b6e01fe30bb", "generation_seconds_batch": 17.85261665796861, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.025602400302886963, "target_z": -0.7734375061259279, "ce": 6.109982967376709, "genuineness": 4.632867813110352, "identity": 0.7674340605735779, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/ed632c3dd4ee792a643b11bca037f8a34f2c1502ac688a1b232f69f040b7d136.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-1", "key": "ed713c2dadc2d2487ff304bfa87d71174e4ae5e5acf5023eccd82b5c13612138", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "72002dc5fc09bf114efc81a28bb9f7670fe624a0eb5ead8c5e86ca6eefd24770", "generation_seconds_batch": 18.919772066990845, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12137937545776367, "target_z": -0.5585937544242813, "ce": 6.252951145172119, "genuineness": 4.632867813110352, "identity": 0.6736350059509277, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/ed713c2dadc2d2487ff304bfa87d71174e4ae5e5acf5023eccd82b5c13612138.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-1", "key": "ed9203338d645b50e821aa82bef4594b36ad333973877dd7a95e98f46b8f94d5", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "0f79011bef780c498d5ba2f371ab581a19c4ca2566c3015315e9ce1e79a96670", "generation_seconds_batch": 18.078579189954326, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5992143154144287, "target_z": 1.6015625047646105, "ce": 6.316492557525635, "genuineness": 3.9299514293670654, "identity": 0.5921673774719238, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het het naast het oude raam. We kunnen er samen in kijken.", "wer": 0.16666666666666666, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/ed9203338d645b50e821aa82bef4594b36ad333973877dd7a95e98f46b8f94d5.mp3" }, { "id": "emo_Impatience_and_Irritability-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-0", "key": "edd6c1967a1fcf939553bc1d9b0529c81c29c0b3061ffbda677fcb9fdb4dc871", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The door is still open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cb0a61307d7f163975130fefef06b4eaf6ae837d323fb7c4aac51ac1e4d42eba", "generation_seconds_batch": 23.466243161004968, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.240065336227417, "target_z": 3.999999912875692, "ce": 5.720792293548584, "genuineness": 3.4310061931610107, "identity": 0.4865880608558655, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/edd6c1967a1fcf939553bc1d9b0529c81c29c0b3061ffbda677fcb9fdb4dc871.mp3" }, { "id": "emo_Impatience_and_Irritability-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-1", "key": "ee975b97d5d28d39e25589fcf1594621a5685636af33b66c18c71bf08eb87ed0", "bucket": "emo_Impatience_and_Irritability", "phase": "wording", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] He encontrado la cajita.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "a4f36e5131bd4b5b2e9bf5312fcc93703b4bd6b64434329b33dfa786faba4960", "generation_seconds_batch": 13.581446272903122, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03586271405220032, "target_z": -0.6835937435337428, "ce": 6.070269584655762, "genuineness": 4.356721878051758, "identity": 0.7028902173042297, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/ee975b97d5d28d39e25589fcf1594621a5685636af33b66c18c71bf08eb87ed0.mp3" }, { "id": "emo_Impatience_and_Irritability-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-0", "key": "efd4fd26243dfdcd2ddc142849f7c2f8b210bb891a6bfbcc80fef842723df06c", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La puerta sigue abierta.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "d3408bd466e74febd5c9bd1fd1e027169c77b33aec12069c1a5949963ce81018", "generation_seconds_batch": 14.374641500995494, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16413772106170654, "target_z": -0.4960937380884735, "ce": 5.577824115753174, "genuineness": 4.231201171875, "identity": 0.6214892864227295, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/efd4fd26243dfdcd2ddc142849f7c2f8b210bb891a6bfbcc80fef842723df06c.mp3" }, { "id": "emo_Impatience_and_Irritability-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-1", "key": "efdc142fc36da46564aa815a7399bea75daf36cb347f359bf2f9472cb84b8535", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] He encontrado la cajita.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "f1341f4ac3da7f1c866fbe61b8bedae5c8a20040edaa95157c4111253e19939c", "generation_seconds_batch": 14.192206317093223, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1320689618587494, "target_z": -0.5429687503403293, "ce": 5.927301406860352, "genuineness": 4.532451152801514, "identity": 0.6983346939086914, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/efdc142fc36da46564aa815a7399bea75daf36cb347f359bf2f9472cb84b8535.mp3" }, { "id": "emo_Impatience_and_Irritability-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-1", "key": "f0dbbdf7b8da0d68951fea64d89df412e5b1b89beddda56b1ff9cc6081ecbe97", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "4a1a6c8b66b8b8419ebf3c4c353c0efbfcc89c2a03bb23261455015dd4f3e3e1", "generation_seconds_batch": 19.292472086963244, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04387989640235901, "target_z": -0.6718750013613173, "ce": 6.348263263702393, "genuineness": 4.231201171875, "identity": 0.5416830778121948, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/f0dbbdf7b8da0d68951fea64d89df412e5b1b89beddda56b1ff9cc6081ecbe97.mp3" }, { "id": "emo_Impatience_and_Irritability-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-1", "key": "f0ec7e76c65a81f7d405fb0c37ffe8cc1b476765822c8f4939df2851d90c9587", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I found the little box.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "6ea306fe448e54dd63a44d42cecae92dc55497ebfb293b3d54809647ce3396e2", "generation_seconds_batch": 19.323610141989775, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0469815731048584, "target_z": -0.8046875142938318, "ce": 6.268836498260498, "genuineness": 4.369274139404297, "identity": 0.38724684715270996, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/f0ec7e76c65a81f7d405fb0c37ffe8cc1b476765822c8f4939df2851d90c9587.mp3" }, { "id": "emo_Impatience_and_Irritability-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-1", "key": "f0fe7418f9fd182173cd97b4dcab4a46a3048094b1eeeb71621704996d91a65a", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "75d6bd0b24366e89f7afd0cdcb0b101625243ec59f96102ba4191cf96715caf7", "generation_seconds_batch": 18.851149516995065, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.027845531702041626, "target_z": -0.6953124857061682, "ce": 6.316492557525635, "genuineness": 4.482243061065674, "identity": 0.4731225073337555, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/f0fe7418f9fd182173cd97b4dcab4a46a3048094b1eeeb71621704996d91a65a.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": "f1b7543ad416c24802eec94dd443b950a9c6e71b0725ba7334da399b451f101a", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d8fd153714cc5b0e67841500994f671d14de0a2d7525bc29955af1b96bf310c5", "generation_seconds_batch": 19.03112119191792, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3586986064910889, "target_z": 1.249999891094615, "ce": 5.1926045417785645, "genuineness": 3.7040140628814697, "identity": 0.269255667924881, "hypothesis": "Die Straße führt hinter der Brücke nach links. Geh weiter bis zu dem kleinen Holztor. Ich ward auf der anderen Seite.", "wer": 0.047619047619047616, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/f1b7543ad416c24802eec94dd443b950a9c6e71b0725ba7334da399b451f101a.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_Impatience_and_Irritability", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": "93d13ca9327712cd13b14fbaa53daac42e77e0887ed21e71e232e8f3221e0e72", "generation_seconds_batch": 14.516162903048098, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13741374015808105, "target_z": -0.5351562700794303, "ce": 6.197352409362793, "genuineness": 4.6203155517578125, "identity": 0.7887153625488281, "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_Impatience_and_Irritability/f21bc0adf2df6aeda4aa5bc68657c60b57559ffed3b647118e970ebfd0ba6ad8.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": "f2a492760c1bc16f15dc10d3bfb5de1af34492fdfdec6fa46e051810c7a58a71", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "15979492c49687326804df262d5faff055d23b5276394aad7ffc5304882f1846", "generation_seconds_batch": 13.423151803086512, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.213865280151367, "target_z": 2.499999869313538, "ce": 5.903473377227783, "genuineness": 3.8922953605651855, "identity": 0.4210062623023987, "hypothesis": "Die Schlüssel liegen auf dem Küchentisch. Ich suchte in der Schublatte daneben dem Fenster. Nimm sie mit, wenn du gehst.", "wer": 0.14285714285714285, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/f2a492760c1bc16f15dc10d3bfb5de1af34492fdfdec6fa46e051810c7a58a71.mp3" }, { "id": "emo_Impatience_and_Irritability-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-1", "key": "f2bc5661aa9a606e28bdd00b64d08ceaa1742b2c7915a85d285616c2456dd2af", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I found the little box.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "f4d24e1981049df3250caa30455dd36f47ee065fd94c234a5c62bf8b89d47f10", "generation_seconds_batch": 17.969674261054024, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2964212894439697, "target_z": -0.30273440511914557, "ce": 5.919358730316162, "genuineness": 3.7667744159698486, "identity": 0.3138474225997925, "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_Impatience_and_Irritability/f2bc5661aa9a606e28bdd00b64d08ceaa1742b2c7915a85d285616c2456dd2af.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-1", "key": "f2e0dfaec3a2968564577a4cba308a4dd00788c128cc8ad38d3a7459bbf46758", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e146d1a256cf0ebb76f04c693ddcec5f72d6ecff440bf40c8edb7497ba001d39", "generation_seconds_batch": 18.228360436973162, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3832741677761078, "target_z": -0.1757812632728438, "ce": 6.09409761428833, "genuineness": 4.024092197418213, "identity": 0.6461212038993835, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/f2e0dfaec3a2968564577a4cba308a4dd00788c128cc8ad38d3a7459bbf46758.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": "f31b308840006d397a9cae7e3ad915a2565a7052c2228361956d5f51c848db29", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Your message arrived after I had left.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1a44ad406945ac406ac925576846071e7ab105fe5972763742976ba0c7fe7949", "generation_seconds_batch": 19.393966111936606, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3105955123901367, "target_z": 1.1796874380600624, "ce": 5.649308204650879, "genuineness": 3.2741053104400635, "identity": 0.4637801945209503, "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_Impatience_and_Irritability/f31b308840006d397a9cae7e3ad915a2565a7052c2228361956d5f51c848db29.mp3" }, { "id": "emo_Impatience_and_Irritability-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-1", "key": "f3266d9fac3f432ab1382a8f2b32c6d329e57ded962eafa8da799d95ea7e1c2b", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I found the little box.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "7ba295f046d40edee276a1aa42d3b464c9bc633f07d4978fd4e7db1c10ff5433", "generation_seconds_batch": 18.679629863006994, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.025602400302886963, "target_z": -0.7734375061259279, "ce": 6.38003396987915, "genuineness": 4.444586753845215, "identity": 0.32164207100868225, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/f3266d9fac3f432ab1382a8f2b32c6d329e57ded962eafa8da799d95ea7e1c2b.mp3" }, { "id": "emo_Impatience_and_Irritability-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-1", "key": "f350db8392582eec085c932c9f2e01966a7a8ae3cf844500d5d812ad91498846", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "7c958f37398d90ed44f2d6bf25fb8788190df498ec7731dc3121306e2dcc7cde", "generation_seconds_batch": 12.773445812985301, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0786210298538208, "target_z": -0.621093770760089, "ce": 5.95112943649292, "genuineness": 4.093128204345703, "identity": 0.4184926152229309, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/f350db8392582eec085c932c9f2e01966a7a8ae3cf844500d5d812ad91498846.mp3" }, { "id": "emo_Impatience_and_Irritability-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-0", "key": "f36503815162c01d1fb139cbeaf87351775bc25fbd594c62a06a4583fff2738e", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La puerta sigue abierta.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "593c1dde7394a83d68a5a743eaba9d15deabfc09f6a2df995e9cc4641a51cd5c", "generation_seconds_batch": 20.789419288979843, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18150827288627625, "target_z": -0.47070314456893636, "ce": 5.967014789581299, "genuineness": 4.356721878051758, "identity": 0.6508873105049133, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/f36503815162c01d1fb139cbeaf87351775bc25fbd594c62a06a4583fff2738e.mp3" }, { "id": "emo_Impatience_and_Irritability-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-1", "key": "f401c07f3004a1689c1e6e9a0d51d3be7ed69d3b5ba7d7692c12023bc7967f03", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] He encontrado la cajita.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "fb5ddad7cfdb109ebfc06ff53cab8581cbf2f3cdcfcdab6919b0f6c4871b2895", "generation_seconds_batch": 18.421126605011523, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.02025759220123291, "target_z": -0.7656249823028749, "ce": 6.173524379730225, "genuineness": 4.469690799713135, "identity": 0.6126871109008789, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/f401c07f3004a1689c1e6e9a0d51d3be7ed69d3b5ba7d7692c12023bc7967f03.mp3" }, { "id": "emo_Impatience_and_Irritability-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-0", "key": "f42b2ae6ea5ef187a25345628db4eeead2c0b13ffe6775be66c7e33215dbef3b", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The door is still open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "2083491361d485fdb91e54cbff975462ca41fba95b6dadf540758f0adbd7a882", "generation_seconds_batch": 13.666600982891396, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6531861424446106, "target_z": 0.21874997005101912, "ce": 5.919358730316162, "genuineness": 3.6663577556610107, "identity": 0.4679785966873169, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/f42b2ae6ea5ef187a25345628db4eeead2c0b13ffe6775be66c7e33215dbef3b.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": "f435839f8d9dd875158057582ec4d4f941ac4b61c96885dfe8c18489d281e1c1", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "6b08411e9dd82694536272f5fcd4a0c36302f9b6eb448d790ca066ad2d2e6084", "generation_seconds_batch": 13.246671225060709, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8536158800125122, "target_z": 0.5117187857345794, "ce": 6.006728172302246, "genuineness": 3.8169827461242676, "identity": 0.37399715185165405, "hypothesis": "Ik schreef het nummer op de envelop. Lees het goed en controleer de laatste twee cijfers. Bel me wanneer je even tijd hebt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/f435839f8d9dd875158057582ec4d4f941ac4b61c96885dfe8c18489d281e1c1.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": "f438f08595018fb5b963cf84d2e92939e01540832d93fe42c0e7fcb116a1b85f", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a64d35c2162fab1a6575f99a0c37f83b798a7be974c95f401a90900550d19c7f", "generation_seconds_batch": 21.892505299067125, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3421404361724854, "target_z": 2.6875000925695773, "ce": 5.752562999725342, "genuineness": 3.6192874908447266, "identity": 0.535682201385498, "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_Impatience_and_Irritability/f438f08595018fb5b963cf84d2e92939e01540832d93fe42c0e7fcb116a1b85f.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-1", "key": "f44e66fdfe5e3a8651d38dda2d6992eb7db6272ea07471fdec0c08715656b3cf", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "96707b8de084ba2859a1a7ecbfabab4ac3ca456c1ac14705f5c6bd99153e2a69", "generation_seconds_batch": 25.826522713992745, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11068978905677795, "target_z": -0.5742187585082332, "ce": 6.078212261199951, "genuineness": 4.381826400756836, "identity": 0.765988826751709, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/f44e66fdfe5e3a8651d38dda2d6992eb7db6272ea07471fdec0c08715656b3cf.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": "f4596932094d90f1703a11abb811e2bd25a192436b6e562d16601f00f31823cf", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "bb18b944c2b907ce6ba694edd9c11ac61768b2e6c4e87f8ae296163179be795a", "generation_seconds_batch": 13.302130249910988, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.9942049980163574, "target_z": 3.6406250367555675, "ce": 5.550024509429932, "genuineness": 3.9048471450805664, "identity": 0.4637201428413391, "hypothesis": "Les clés sont sur la table de la cuisine. J'ai regardé dans le tiroir puis près de la fenêtre. Prends-les quand tu partiras.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/f4596932094d90f1703a11abb811e2bd25a192436b6e562d16601f00f31823cf.mp3" }, { "id": "emo_Impatience_and_Irritability-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-0", "key": "f45a0f9d1522e1f70d25b55bc88c0efc97bb5318b2cdd3fa15467fc628d758f2", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The door is still open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "62045342e679745892602b4d7113ca213223304385cfe52872520070adc99940", "generation_seconds_batch": 13.49553538695909, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0973278284072876, "target_z": -0.5937499809415576, "ce": 6.221180438995361, "genuineness": 4.256305694580078, "identity": 0.2771938443183899, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/f45a0f9d1522e1f70d25b55bc88c0efc97bb5318b2cdd3fa15467fc628d758f2.mp3" }, { "id": "emo_Impatience_and_Irritability-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-1", "key": "f4801e97fa1fdfe1cae3a069c98d3502f02c567a6d627c21769b82c4da6af6a9", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "98944869f348a3b656e977e0eec17151f7f3756c480840c2a4d4e8aaac245ca7", "generation_seconds_batch": 19.292472086963244, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11870697140693665, "target_z": -0.5625000163358077, "ce": 6.23706579208374, "genuineness": 4.124508857727051, "identity": 0.4052620530128479, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/f4801e97fa1fdfe1cae3a069c98d3502f02c567a6d627c21769b82c4da6af6a9.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": "f49082136f48bc5f5deb6c65169bb11cf5257d8ae5d1df2e1fd6a3f48452e6cf", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1f270c7286e3f0267d799db1ac385516e7be100191e14f7b1c1b5dc663d70baf", "generation_seconds_batch": 13.246671225060709, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8108575344085693, "target_z": 0.4492187693987717, "ce": 5.808161735534668, "genuineness": 3.7291181087493896, "identity": 0.6824046969413757, "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_Impatience_and_Irritability/f49082136f48bc5f5deb6c65169bb11cf5257d8ae5d1df2e1fd6a3f48452e6cf.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-1", "key": "f4bd609b889be961fd80cd8b3f4ee969949a9fa623cc3ac4561efbfbbd720fb4", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "4986b98880ef0f3fe79ae2c3069721d2795a29d6ceff603ecb77a6264492265c", "generation_seconds_batch": 18.958957261987962, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.011811137199401855, "target_z": -0.7187500136131731, "ce": 6.157639026641846, "genuineness": 4.432034492492676, "identity": 0.5904505252838135, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/f4bd609b889be961fd80cd8b3f4ee969949a9fa623cc3ac4561efbfbbd720fb4.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-1", "key": "f5900763a157d5f7cbde06b8e2f8fb9f2c7615f65f063004e956abb6283e1f32", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "e02d6702f8c7f9e2881f0efbc7fc0da9d35cbafd8e4ac7c23443e1895c7ee4ab", "generation_seconds_batch": 15.25431748200208, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.674565315246582, "target_z": 0.249999978218923, "ce": 6.054384231567383, "genuineness": 4.068024158477783, "identity": 0.7244458198547363, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/f5900763a157d5f7cbde06b8e2f8fb9f2c7615f65f063004e956abb6283e1f32.mp3" }, { "id": "emo_Impatience_and_Irritability-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-0", "key": "f6f62709a99023b758417b667ccafd43b7d211382ecf03c3944530bf280455ed", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Tür ist noch offen.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "9b52a3e07955b7d6cd353480ec626db4b16408da8900e16c00d6a2c22d02587b", "generation_seconds_batch": 18.216588776092976, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.818874716758728, "target_z": 0.46093751157119717, "ce": 6.2767791748046875, "genuineness": 4.507347106933594, "identity": 0.6180623769760132, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/f6f62709a99023b758417b667ccafd43b7d211382ecf03c3944530bf280455ed.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": "f70ca490a3eb6c603e9a61078a64189da5089cbb3a33ce0ff792d54d13584027", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "23311a09057174420838f1ac99cd585e2a86460f81def19f7fe5a643183d625a", "generation_seconds_batch": 19.486686244956218, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.064211130142212, "target_z": 2.281249899262519, "ce": 5.855817794799805, "genuineness": 3.5722172260284424, "identity": 0.39936596155166626, "hypothesis": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier naast de hoge boekenkast. We zetten het naar de lunch terug.", "wer": 0.047619047619047616, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/f70ca490a3eb6c603e9a61078a64189da5089cbb3a33ce0ff792d54d13584027.mp3" }, { "id": "emo_Impatience_and_Irritability-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-1", "key": "f71c7d27e9c5f2c5e18ad3bebbf7971c05de026bd159e12297245ed58a89be1b", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] He encontrado la cajita.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "491ba7b77b5e4bb8875aa08532ee77b42006d4c37230828bd289b7c069eeb65b", "generation_seconds_batch": 19.55721421202179, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11870697140693665, "target_z": -0.5625000163358077, "ce": 5.967014789581299, "genuineness": 4.6705241203308105, "identity": 0.7041716575622559, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/f71c7d27e9c5f2c5e18ad3bebbf7971c05de026bd159e12297245ed58a89be1b.mp3" }, { "id": "emo_Impatience_and_Irritability-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-1", "key": "f761734fffb3af6c4c7f73031bd7feb0d600686e59df88241d26b34e59487f38", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "0bb1d264cfc8468746af92311d327133233807180ca6ffc211e78b4c0caa0353", "generation_seconds_batch": 18.34267005394213, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05456948280334473, "target_z": -0.6562499972773653, "ce": 6.24500846862793, "genuineness": 3.9927117824554443, "identity": 0.5624525547027588, "hypothesis": "Ich habe die kleine Schachtel gefunden, sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/f761734fffb3af6c4c7f73031bd7feb0d600686e59df88241d26b34e59487f38.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_Impatience_and_Irritability", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": "12dcdb01bcac2f1a9d4848066c09718942199428761ce5c8c79d9b13e42a0146", "generation_seconds_batch": 13.67164071998559, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1320689618587494, "target_z": -0.5429687503403293, "ce": 6.0146708488464355, "genuineness": 4.507347106933594, "identity": 0.7670470476150513, "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_Impatience_and_Irritability/f7a65885d0e107603bdce9d92b5fc3b68a68524db7b0b06f79b6538794e8bf5c.mp3" }, { "id": "emo_Impatience_and_Irritability-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-0", "key": "f7a9119b8343480b6df115143bc77f3c84abfa37b2034e0a9937ab24910d700f", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La puerta sigue abierta.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "179b210b611363331fd7285e2852a5b03ed17dd595ebd6f89e6f6d659f140bde", "generation_seconds_batch": 17.921745307045057, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.49818721413612366, "target_z": -0.0078124802608989675, "ce": 6.046441555023193, "genuineness": 4.300237655639648, "identity": 0.5680046081542969, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/f7a9119b8343480b6df115143bc77f3c84abfa37b2034e0a9937ab24910d700f.mp3" }, { "id": "emo_Impatience_and_Irritability-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-1", "key": "f7f9981a063171de1f1c4229757c21c30a4af36393d1c02386f6e7a9f4f81ac4", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I found the little box.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "8cdb563b39899adab23fce557c4121baa2a75c1d829d58fcd23a12abbf3c405a", "generation_seconds_batch": 18.712557755061425, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.06836074590682983, "target_z": -0.8359375224617357, "ce": 6.24500846862793, "genuineness": 4.061748504638672, "identity": 0.38329482078552246, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/f7f9981a063171de1f1c4229757c21c30a4af36393d1c02386f6e7a9f4f81ac4.mp3" }, { "id": "emo_Impatience_and_Irritability-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-1", "key": "f7fcc6dfc63d35e5ab4355be549ca8b068f1143e02353f2c8843a02e2677de27", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I found the little box.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "b563d24cee9f562205355ab357cbce9f5a2a5e0d77fc7074cffbeeb2ced06e51", "generation_seconds_batch": 17.98840181902051, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14543095231056213, "target_z": -0.5234374843448509, "ce": 6.38003396987915, "genuineness": 4.519899368286133, "identity": 0.38290369510650635, "hypothesis": "I found the little box it was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/f7fcc6dfc63d35e5ab4355be549ca8b068f1143e02353f2c8843a02e2677de27.mp3" }, { "id": "emo_Impatience_and_Irritability-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-1", "key": "f8508b26512a55b712731a93396e92aa13af2554c0f805f12056f382af32d955", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I found the little box.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "a1bb1d2a64deb5507412b42faf2dea6444d76a5d83ce00b567d7a21659bc9e80", "generation_seconds_batch": 18.119181509013288, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17081871628761292, "target_z": -0.4863281050907343, "ce": 5.990842819213867, "genuineness": 3.8420867919921875, "identity": 0.5023217797279358, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/f8508b26512a55b712731a93396e92aa13af2554c0f805f12056f382af32d955.mp3" }, { "id": "emo_Impatience_and_Irritability-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-1", "key": "f8539a1b211c430192bcfd5c1496f87578eb30e2b8c815d6a88941d25903c019", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "973dbb1121e3192ab3514a85a85ee57231098ae14913c1d50eb69a26f35f6ca3", "generation_seconds_batch": 19.729572236072272, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4495601654052734, "target_z": 1.3828125347135916, "ce": 5.474569320678711, "genuineness": 3.6224255561828613, "identity": 0.49864456057548523, "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_Impatience_and_Irritability/f8539a1b211c430192bcfd5c1496f87578eb30e2b8c815d6a88941d25903c019.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_Impatience_and_Irritability", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": "6be75e769054810a2df76132c3e436a3447a0118aeba28b960ede917567fec4a", "generation_seconds_batch": 14.72581505193375, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09198302030563354, "target_z": -0.6015625047646106, "ce": 6.324435234069824, "genuineness": 4.482243061065674, "identity": 0.5666730403900146, "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_Impatience_and_Irritability/f86feddc7af334e5c3d6691e715ece3168f8e7618bd3b63ca7d0171f412fdf9d.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": "f879e534cc77be137eb01ff1da0e09fae91556359bd8a0f87cb8b0a76ea718fe", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "503e39b3ac27517a2b4390b036e8acad4c58e29e9ef679e0eeeb26a80273fbd1", "generation_seconds_batch": 19.659422751981765, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5724904537200928, "target_z": 1.5625001470222697, "ce": 5.871703147888184, "genuineness": 3.9299514293670654, "identity": 0.6804299354553223, "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_Impatience_and_Irritability/f879e534cc77be137eb01ff1da0e09fae91556359bd8a0f87cb8b0a76ea718fe.mp3" }, { "id": "emo_Impatience_and_Irritability-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-0", "key": "f8a6624c6e25195df5ce348b8e7146d4848cc904283b6fcabb172edfc95b5cc3", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Tür ist noch offen.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "077aa442b639c890682fc94fdd4f1c168510d432fa0e3b6700f1768d94cd72b3", "generation_seconds_batch": 18.121031234040856, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22827520966529846, "target_z": -0.4023437571469159, "ce": 6.356205940246582, "genuineness": 4.582659721374512, "identity": 0.45891666412353516, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/f8a6624c6e25195df5ce348b8e7146d4848cc904283b6fcabb172edfc95b5cc3.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-1", "key": "f8b12516f601538e86af8a5f5bf632d4bd1fa03d218449b6b5dfbd104f1c0f25", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "b3a21385057a6b6281b7939795c982873519e7719370f88018a224de85c734b6", "generation_seconds_batch": 17.535330845974386, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.32715386152267456, "target_z": -0.257812502041976, "ce": 6.09409761428833, "genuineness": 4.319066047668457, "identity": 0.7302613854408264, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/f8b12516f601538e86af8a5f5bf632d4bd1fa03d218449b6b5dfbd104f1c0f25.mp3" }, { "id": "emo_Impatience_and_Irritability-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-0", "key": "f8cacd889a930a197bd7c8174f540a22a83ce234a158bf5baa9cd8344572b341", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The door is still open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "50b4525f2767043ba1a142f2d95b3144446a2c02362a53c8525fee6b3a5bc81f", "generation_seconds_batch": 18.799302662024274, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5618007183074951, "target_z": 1.5468749251275478, "ce": 5.77639102935791, "genuineness": 3.6287014484405518, "identity": 0.3339240550994873, "hypothesis": "Pff the door is still open. I put your coat on the chair. Wait 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_Impatience_and_Irritability/f8cacd889a930a197bd7c8174f540a22a83ce234a158bf5baa9cd8344572b341.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-1", "key": "f94dd1bb1a4e10e5fc97ea8a9eae17081ce3bb28eb624b2f69fda43ae1f60d08", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "9eadc972dfca3db649a6438ad3e07005b7dae0a1649e725f67e6d5642a8413e2", "generation_seconds_batch": 13.223683195072226, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08663824200630188, "target_z": -0.6093749850255096, "ce": 6.09409761428833, "genuineness": 4.532451152801514, "identity": 0.7177196145057678, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/f94dd1bb1a4e10e5fc97ea8a9eae17081ce3bb28eb624b2f69fda43ae1f60d08.mp3" }, { "id": "emo_Impatience_and_Irritability-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-0", "key": "f9523236d01b89f545c0cad745ff649e282f33639f94ad233cd158145735447d", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Tür ist noch offen.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "1f333ac1bbfacb0a93843d44d46f76b1ac5917ed3f14e8d535a913bd41c00646", "generation_seconds_batch": 13.478433658950962, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.909736156463623, "target_z": 0.5937499809415576, "ce": 6.213237762451172, "genuineness": 4.444586753845215, "identity": 0.30245473980903625, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/f9523236d01b89f545c0cad745ff649e282f33639f94ad233cd158145735447d.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-1", "key": "f957441771e1756f2b2d6351d200c24e23530184bcdf9a7a80610b58ccac30c9", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "5a16ff584aff590c5ce53f565a6eac8d22b6a810a6f8555e080277ebdf76cfc3", "generation_seconds_batch": 22.31411813304294, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4126705229282379, "target_z": -0.13281251293251448, "ce": 6.165581703186035, "genuineness": 4.15588903427124, "identity": 0.6449404954910278, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/f957441771e1756f2b2d6351d200c24e23530184bcdf9a7a80610b58ccac30c9.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-0", "key": "fa4a8c6b73252d2f5eceda06185fb6f498fbeb00a23a6ca8d7b1df8080c70dc0", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La porte est encore ouverte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "4f27e103a8dea0001c0b55778bb96d634edc661d3e080a1ef7f98d5f69ea5f33", "generation_seconds_batch": 18.267728995066136, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3111194968223572, "target_z": -0.28124998638682686, "ce": 6.006728172302246, "genuineness": 4.444586753845215, "identity": 0.6445413827896118, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/fa4a8c6b73252d2f5eceda06185fb6f498fbeb00a23a6ca8d7b1df8080c70dc0.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-1", "key": "fa5bcba4b6c08c1369fdb071a843fd1ae380502d44ab0fb3ffe66b3d640d10e2", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "23782eef34a6d6d69ddbbd90671275dce27d4b45436d6ab84bec00bc39249693", "generation_seconds_batch": 21.54308373806998, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.25499916076660156, "target_z": -0.36328126871811306, "ce": 5.967014789581299, "genuineness": 4.582659721374512, "identity": 0.8077651262283325, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/fa5bcba4b6c08c1369fdb071a843fd1ae380502d44ab0fb3ffe66b3d640d10e2.mp3" }, { "id": "emo_Impatience_and_Irritability-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-0", "key": "faab361678b0accf5646f729717b1cb44954b3a9f78132417dd0702cde76250d", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Tür ist noch offen.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "e5aecad5be6027db6503fa88f26a4735588f957c6a6cae89bf7321b569b2c326", "generation_seconds_batch": 18.087766544078477, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1021486520767212, "target_z": 0.8749999673283845, "ce": 6.284721851348877, "genuineness": 4.507347106933594, "identity": 0.6306676864624023, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/faab361678b0accf5646f729717b1cb44954b3a9f78132417dd0702cde76250d.mp3" }, { "id": "emo_Impatience_and_Irritability-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-0", "key": "fb5c4993c18950f5618f2ae5e6cf12d8e98f6d8616caf9af5c22b2f10fe81272", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The door is still open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": 129, "seconds_generated": 10.32, "mp3_sha256": "8ef1edc8e7b2d09ef640e1fa381d81b730eae543a9920b4cf87f923780c432ae", "generation_seconds_batch": 19.314413256011903, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11870697140693665, "target_z": -0.5625000163358077, "ce": 6.109982967376709, "genuineness": 3.9173994064331055, "identity": 0.3201584815979004, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/fb5c4993c18950f5618f2ae5e6cf12d8e98f6d8616caf9af5c22b2f10fe81272.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-1", "key": "fc399a6a5c085d6130572c64c6560a3959da5512a485efd16bd8f6a0eec2c613", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "4ba172c80fac6d85d395b652894a984b81ed5e04110bf5787cd1a6ee2863f388", "generation_seconds_batch": 17.937514627934434, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.34318822622299194, "target_z": -0.23437501769712507, "ce": 6.221180438995361, "genuineness": 4.250029563903809, "identity": 0.646964430809021, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/fc399a6a5c085d6130572c64c6560a3959da5512a485efd16bd8f6a0eec2c613.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-1", "key": "fc9aaf84b850c99a88b5568e7cc4f666c3c105e0a06357d69c7d6bddd370d3ea", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "acdf0a4632da1dc54580a9f474d7a76c91d005f3999155e7d564f08f9c4852eb", "generation_seconds_batch": 19.834195206989534, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.30844709277153015, "target_z": -0.28515624829835334, "ce": 5.998785495758057, "genuineness": 4.017816066741943, "identity": 0.7035233974456787, "hypothesis": "J'ai. j'ai trouvé la petite boîte. Elle était près de... La vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.05263157894736842, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/fc9aaf84b850c99a88b5568e7cc4f666c3c105e0a06357d69c7d6bddd370d3ea.mp3" }, { "id": "emo_Impatience_and_Irritability-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-0", "key": "fca64a191a38ae7e25656951de4e620a18d1e5eb7020c2634217eadf4c730772", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Die Tür ist noch offen.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "731959208ea5d0bda01fd789a4028ec69424c7dd204871993061732ab48c0655", "generation_seconds_batch": 18.041134004946798, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.684206962585449, "target_z": 3.187499874758807, "ce": 5.863759994506836, "genuineness": 4.18099308013916, "identity": 0.4560312032699585, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/fca64a191a38ae7e25656951de4e620a18d1e5eb7020c2634217eadf4c730772.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": "fcb142fdce5614f364120c1eab754d28abe6e8fd77f7a052197ab9180970dae0", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bb11c503e72bbabe72f019a9e2527fd11d2c8f2c95ca7eddc240167736e327b6", "generation_seconds_batch": 20.221674534026533, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6200695037841797, "target_z": 3.0937499373794037, "ce": 5.355429172515869, "genuineness": 3.8420867919921875, "identity": 0.5804733633995056, "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_Impatience_and_Irritability/fcb142fdce5614f364120c1eab754d28abe6e8fd77f7a052197ab9180970dae0.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": "fd6a98ed0f1787fbbcb86f2b1a2f74a69c180987ee0094e6b99a4fc2fd981615", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "761ee9dbade194a435dd42f90fba6e76671aef82cbb573902384779dac3f63ce", "generation_seconds_batch": 14.20422387495637, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6580069065093994, "target_z": 1.6874998311966531, "ce": 5.752562999725342, "genuineness": 3.660081624984741, "identity": 0.5251199007034302, "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_Impatience_and_Irritability/fd6a98ed0f1787fbbcb86f2b1a2f74a69c180987ee0094e6b99a4fc2fd981615.mp3" }, { "id": "emo_Impatience_and_Irritability-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-0", "key": "fd7923c099c384d0d654cbf73520a9b9769332495a589d0acaf6043b221f0b16", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] The door is still open.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] I put your coat on the chair.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "9bc41f0ef785dbd9bac4a0f96db874439a65df41d8dbba169b007920edb86c0d", "generation_seconds_batch": 13.959948294912465, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.299381971359253, "target_z": 2.6249999019851535, "ce": 5.871703147888184, "genuineness": 3.487490653991699, "identity": 0.4115324020385742, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/fd7923c099c384d0d654cbf73520a9b9769332495a589d0acaf6043b221f0b16.mp3" }, { "id": "emo_Impatience_and_Irritability-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-0", "key": "fdaba25d4aa6fe35e7c2f768184c114d5347967301c363c39b188dec60d7b40e", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] La puerta sigue abierta.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "e1b4a95ced8d0f8429ac8fb0cfb3aae3edc0027bbe7e841e59b6b96283bff617", "generation_seconds_batch": 18.009480266016908, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3952999711036682, "target_z": -0.15820310645205163, "ce": 6.070269584655762, "genuineness": 4.193545341491699, "identity": 0.5580917596817017, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/fdaba25d4aa6fe35e7c2f768184c114d5347967301c363c39b188dec60d7b40e.mp3" }, { "id": "emo_Impatience_and_Irritability-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-es-1", "key": "fdd2bf6d346a3bcb62df9c3939347b549c3902d4f3c94f23e532508d976e8582", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] He encontrado la cajita.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "8ce09786b78e580433fcf492727ab1acb8a16940bb87963cc12cedc44b856a73", "generation_seconds_batch": 19.064070543041453, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.39930856227874756, "target_z": -0.1523437353658389, "ce": 5.831989288330078, "genuineness": 4.319066047668457, "identity": 0.6504629254341125, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/fdd2bf6d346a3bcb62df9c3939347b549c3902d4f3c94f23e532508d976e8582.mp3" }, { "id": "emo_Impatience_and_Irritability-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-en-1", "key": "fde3009ea548d5f4ece2be7cef26b1e844cf192f4b84af14dbb6c535988d20c6", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] I found the little box.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] It was beside the old window.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "28137aa830ab42e1546e5b1d02240a3427f0652c99cde4314acb4f35ba684a38", "generation_seconds_batch": 19.12720317498315, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.00646635890007019, "target_z": -0.7265624938740721, "ce": 6.356205940246582, "genuineness": 4.582659721374512, "identity": 0.33508116006851196, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/fde3009ea548d5f4ece2be7cef26b1e844cf192f4b84af14dbb6c535988d20c6.mp3" }, { "id": "emo_Impatience_and_Irritability-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-nl-1", "key": "fe6364ee5b73818550a5e00ce9cb911576285ac540d2b3d4b2ae0e8f3ceb11a9", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Het stond naast het oude raam.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "280a114e81fc776a619b0c24e58c5d119bf3ced33da3f2a30f5e29901631aff9", "generation_seconds_batch": 13.11355577094946, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5168939828872681, "target_z": 0.01953126599547842, "ce": 6.149696350097656, "genuineness": 4.042920112609863, "identity": 0.6681724190711975, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/fe6364ee5b73818550a5e00ce9cb911576285ac540d2b3d4b2ae0e8f3ceb11a9.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": "ff5a7696af50a33eae8fa9df6557edc55853896c7edf40f74f4b89424b7a2ad8", "bucket": "emo_Impatience_and_Irritability", "phase": "heldout", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8fde96b03928bd4b16c119c5451a78693a5d1231ab87e4ea06bd8b35dd548f9a", "generation_seconds_batch": 14.155993068008684, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.449036121368408, "target_z": 2.8437498720361725, "ce": 5.150905609130859, "genuineness": 3.7165660858154297, "identity": 0.3797036111354828, "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_Impatience_and_Irritability/ff5a7696af50a33eae8fa9df6557edc55853896c7edf40f74f4b89424b7a2ad8.mp3" }, { "id": "emo_Impatience_and_Irritability-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-1", "key": "ff6c545a68b006c443c6f6ebde0f019d2fb63205dfed95fbbcf371ced33bfbe6", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "a85c7c47748d6eb82f31ca2290a99833e9f037b7181cfac54f13fa5badcd96b0", "generation_seconds_batch": 17.890162783907726, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09465542435646057, "target_z": -0.5976562428530842, "ce": 6.23706579208374, "genuineness": 4.15588903427124, "identity": 0.6433560848236084, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/ff6c545a68b006c443c6f6ebde0f019d2fb63205dfed95fbbcf371ced33bfbe6.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-1", "key": "ff8d5b486016a1648ab2dc278173fcbb673ff63b23d8e69152e426ad44e4bcd4", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": 127, "seconds_generated": 10.16, "mp3_sha256": "aa76f30604a17ae4c9ae96695e282d8a6b03af3641261ec2b266ffea7cd832a7", "generation_seconds_batch": 17.64403980690986, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9471497535705566, "target_z": 0.6484375605786205, "ce": 5.585766792297363, "genuineness": 3.8169827461242676, "identity": 0.5526837110519409, "hypothesis": "J'ai trouvé la 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_Impatience_and_Irritability/ff8d5b486016a1648ab2dc278173fcbb673ff63b23d8e69152e426ad44e4bcd4.mp3" }, { "id": "emo_Impatience_and_Irritability-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-fr-1", "key": "ffdbd233b7b50d6eae5d866cff640d999c0e42d79434bbf627a25d733a5e371d", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2c3415de70f19703649b1f68f951773441270d3cd27a8acc1cce2f6cc5382832", "generation_seconds_batch": 17.64403980690986, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.459725856781006, "target_z": 2.8593750939308946, "ce": 5.506340026855469, "genuineness": 3.9173994064331055, "identity": 0.6768307089805603, "hypothesis": "J'ai trouvé la petite boîte, elle était près de plein vieilles fenêtres. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.15789473684210525, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Impatience_and_Irritability/ffdbd233b7b50d6eae5d866cff640d999c0e42d79434bbf627a25d733a5e371d.mp3" }, { "id": "emo_Impatience_and_Irritability-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Impatience_and_Irritability-de-1", "key": "ffe8bff45ad0d0b741148f66a2cf06fe8c5c3c4eea647316682f066dfedf8c0f", "bucket": "emo_Impatience_and_Irritability", "phase": "grid", "candidate": "manual-89f8b6c2e4b7", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Focus on aggressive articulation and a pressurized breath support. The intent is to sound perpetually on the verge of snapping. Maintain forward placement aggressively.\nSCRIPT:\n(Initiate with a forced, slightly breathy quality that immediately hardens into sharp consonants. Convey immediate tension.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Drive the pace forward relentlessly, using vocal fry sparingly to emphasize moments of extreme annoyance. The sound should feel pushed.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Deliver the final segment with maximum forward projection, as if speaking directly at an unseen irritant.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "7df62b6d919ccfb8aa92e753713a00ee68891258d350c21b5746be49a594a8cc", "generation_seconds_batch": 19.729572236072272, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.577022910118103, "target_z": 0.10742191941297732, "ce": 5.839932441711426, "genuineness": 3.7291181087493896, "identity": 0.45907264947891235, "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_Impatience_and_Irritability/ffe8bff45ad0d0b741148f66a2cf06fe8c5c3c4eea647316682f066dfedf8c0f.mp3" }, { "key": "original-emo_Impatience_and_Irritability-de-0-seed1701-scale0.0", "bucket": "emo_Impatience_and_Irritability", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "75108326c4ab00c961611886a325a55a7a92f29d88690f0677a287df02451014", "task_id": "emo_Impatience_and_Irritability-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": 0.30042991042137146, "target_z": -0.2968749904707788, "ce": 6.300607204437256, "genuineness": 4.381826400756836, "identity": 0.6032346487045288, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/de/f493917cb6378a10b1d9a577.mp3" }, { "key": "original-emo_Impatience_and_Irritability-de-0-seed1701-scale0.5", "bucket": "emo_Impatience_and_Irritability", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "5fac8ef0e5e38de97d226b3e9126ca25541a4920f37ce4ff4c5f3fa3a3065cd3", "task_id": "emo_Impatience_and_Irritability-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": 0.5589842200279236, "target_z": 0.08105470596286606, "ce": 6.197352409362793, "genuineness": 4.193545341491699, "identity": 0.6655222177505493, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/de/279b2524d034b10bfc4f60e0.mp3" }, { "key": "original-emo_Impatience_and_Irritability-de-0-seed1701-scale0.75", "bucket": "emo_Impatience_and_Irritability", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "0fb32ffa124244a9d4d9fc47c40dd9d188cb632a8abc5c7acffaefc13b0d2f30", "task_id": "emo_Impatience_and_Irritability-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": 0.18551689386367798, "target_z": -0.46484372992056966, "ce": 6.23706579208374, "genuineness": 4.545003414154053, "identity": 0.5776036977767944, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/de/ae4c14db791ee714b28e3649.mp3" }, { "key": "original-emo_Impatience_and_Irritability-de-0-seed1701-scale1.0", "bucket": "emo_Impatience_and_Irritability", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "8c9aaf56c7083c790a7d65b34a8ace3c153e49be021ce9d2ca53ed3590f1960c", "task_id": "emo_Impatience_and_Irritability-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": 0.43404969573020935, "target_z": -0.1015625047646106, "ce": 6.149696350097656, "genuineness": 4.507347106933594, "identity": 0.44815656542778015, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/de/20afc75d6611b49686fb5e2a.mp3" }, { "key": "original-emo_Impatience_and_Irritability-de-0-seed1702-scale0.0", "bucket": "emo_Impatience_and_Irritability", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "0bbba0d18c4725677ecdcde734bb70bbfe9b6edb890b2ed443f165ccc8e45bfc", "task_id": "emo_Impatience_and_Irritability-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": 0.21758562326431274, "target_z": -0.41796876123086785, "ce": 6.229123115539551, "genuineness": 4.469690799713135, "identity": 0.5714461207389832, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/de/c614591ff2fc39b40db293ba.mp3" }, { "key": "original-emo_Impatience_and_Irritability-de-0-seed1702-scale0.5", "bucket": "emo_Impatience_and_Irritability", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "ab6f4a3b7d5fdfa6ab100c30c5ed8154d8397a74111832c7d1384e92a6300676", "task_id": "emo_Impatience_and_Irritability-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": 0.16681009531021118, "target_z": -0.492187519739101, "ce": 6.23706579208374, "genuineness": 4.381826400756836, "identity": 0.660772442817688, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/de/8869660c34754b9c74cbe8d5.mp3" }, { "key": "original-emo_Impatience_and_Irritability-de-0-seed1702-scale0.75", "bucket": "emo_Impatience_and_Irritability", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "f595377793fafe5ad5dc164464e2d770758c32c80644983bbe949a95bd194d7b", "task_id": "emo_Impatience_and_Irritability-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": 0.18284448981285095, "target_z": -0.46874999183209615, "ce": 6.348263263702393, "genuineness": 4.469690799713135, "identity": 0.40137141942977905, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/de/91665edbc919f6363a23bd6f.mp3" }, { "key": "original-emo_Impatience_and_Irritability-de-0-seed1702-scale1.0", "bucket": "emo_Impatience_and_Irritability", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "09b6abe10ffee271a46e88267e418a105ca38a9899e2a1502360abec94736a8d", "task_id": "emo_Impatience_and_Irritability-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": 0.3151280879974365, "target_z": -0.27539061530061415, "ce": 6.24500846862793, "genuineness": 4.306513786315918, "identity": 0.6800066232681274, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/de/72d0cd448471ef3fbba57d38.mp3" }, { "key": "original-emo_Impatience_and_Irritability-de-1-seed1701-scale0.0", "bucket": "emo_Impatience_and_Irritability", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "e4e1985d16ccf267ed67e27499f2536ddaee96d843dcce41b4b361fdb62c0102", "task_id": "emo_Impatience_and_Irritability-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": 0.011811137199401855, "target_z": -0.7187500136131731, "ce": 6.435632705688477, "genuineness": 4.218649387359619, "identity": 0.46791982650756836, "hypothesis": "Ich habe die kleine Schachtel gefunden, sie stand neben dem alten Fenster, wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/de/912158d8b5ab124c567047e9.mp3" }, { "key": "original-emo_Impatience_and_Irritability-de-1-seed1701-scale0.5", "bucket": "emo_Impatience_and_Irritability", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "2530f0ed61fa99b4e65951805a5a2f1bb9b3ef61108f68bf02e958c6643e2d35", "task_id": "emo_Impatience_and_Irritability-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": 0.08663824200630188, "target_z": -0.6093749850255096, "ce": 6.340320587158203, "genuineness": 4.042920112609863, "identity": 0.5154790878295898, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/de/d5b2ad3c6b15a6e6b2085988.mp3" }, { "key": "original-emo_Impatience_and_Irritability-de-1-seed1701-scale0.75", "bucket": "emo_Impatience_and_Irritability", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "fbbe354f8443611668524eb65010a709c45cd252ead91bc2721acd38776ce346", "task_id": "emo_Impatience_and_Irritability-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": 0.04387989640235901, "target_z": -0.6718750013613173, "ce": 6.403861999511719, "genuineness": 4.532451152801514, "identity": 0.594387412071228, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/de/533c121a8516731a589c82b3.mp3" }, { "key": "original-emo_Impatience_and_Irritability-de-1-seed1701-scale1.0", "bucket": "emo_Impatience_and_Irritability", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "203beb7d3e23b6e871050aedd1faaf9f529f885be9184dbb60f43bb4cf15cb3f", "task_id": "emo_Impatience_and_Irritability-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": -0.012240409851074219, "target_z": -0.7539062401304495, "ce": 6.356205940246582, "genuineness": 4.369274139404297, "identity": 0.3613972067832947, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/de/c2d22fad2547e35a4127d965.mp3" }, { "key": "original-emo_Impatience_and_Irritability-de-1-seed1702-scale0.0", "bucket": "emo_Impatience_and_Irritability", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "ab3e6fdef118e1143b2567dc08b92f8d06dcebce7a20f0b4267ceb2a0f33518e", "task_id": "emo_Impatience_and_Irritability-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": -0.0282747745513916, "target_z": -0.7773437244753004, "ce": 6.340320587158203, "genuineness": 4.218649387359619, "identity": 0.4443323612213135, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/de/6ee1e6be0ec29699b42c9a43.mp3" }, { "key": "original-emo_Impatience_and_Irritability-de-1-seed1702-scale0.5", "bucket": "emo_Impatience_and_Irritability", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "e33091356c6ea89d2c075a0fb635222476203d881221a96e45be5c665fd9a003", "task_id": "emo_Impatience_and_Irritability-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": 0.003793954849243164, "target_z": -0.7304687557855986, "ce": 6.252951145172119, "genuineness": 4.168440818786621, "identity": 0.5101281404495239, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/de/e3b78f480f72d92334ea7d62.mp3" }, { "key": "original-emo_Impatience_and_Irritability-de-1-seed1702-scale0.75", "bucket": "emo_Impatience_and_Irritability", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "5739cad9b81338f3eb645e8e07a26204fc3e546f1fc2a35c7d20303e4109cfb0", "task_id": "emo_Impatience_and_Irritability-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": -0.00956803560256958, "target_z": -0.750000021781077, "ce": 6.475345611572266, "genuineness": 4.193545341491699, "identity": 0.37681421637535095, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/de/a839e278c24890ee14bd198c.mp3" }, { "key": "original-emo_Impatience_and_Irritability-de-1-seed1702-scale1.0", "bucket": "emo_Impatience_and_Irritability", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "13ae837b7c6b9e74269293ca0dad84964c6969e944cad7556eb3a45ca7951a1e", "task_id": "emo_Impatience_and_Irritability-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": 0.08129343390464783, "target_z": -0.6171875088485625, "ce": 6.348263263702393, "genuineness": 4.243753433227539, "identity": 0.6509532928466797, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/de/8d300a78a7b8096d4071acb2.mp3" }, { "key": "original-emo_Impatience_and_Irritability-en-0-seed1701-scale0.0", "bucket": "emo_Impatience_and_Irritability", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "7ad05b3ad4c77b7ea0fe7f627099cdde844b9ad300f50a6f82b81a59d5bad759", "task_id": "emo_Impatience_and_Irritability-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": 0.07060384750366211, "target_z": -0.6328125129325145, "ce": 6.109982967376709, "genuineness": 3.8169827461242676, "identity": 0.2895049452781677, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/en/7ca35879e7707838e7493014.mp3" }, { "key": "original-emo_Impatience_and_Irritability-en-0-seed1701-scale0.5", "bucket": "emo_Impatience_and_Irritability", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "77a769ed9478bde19fc4f6107e5c31422ec7104c5760b441814ac3ee25c305b4", "task_id": "emo_Impatience_and_Irritability-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": 0.08663824200630188, "target_z": -0.6093749850255096, "ce": 6.1894097328186035, "genuineness": 3.9676074981689453, "identity": 0.2153903841972351, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/en/a7239609be32ccc480392422.mp3" }, { "key": "original-emo_Impatience_and_Irritability-en-0-seed1701-scale0.75", "bucket": "emo_Impatience_and_Irritability", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "1be8173c530f26b2936ac44bbd00f5c79bea83271ee163661cd83c50b3c5273a", "task_id": "emo_Impatience_and_Irritability-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": 0.08396583795547485, "target_z": -0.613281246937036, "ce": 6.221180438995361, "genuineness": 4.137060642242432, "identity": 0.21211759746074677, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/en/451d725888652c466c5b47be.mp3" }, { "key": "original-emo_Impatience_and_Irritability-en-0-seed1701-scale1.0", "bucket": "emo_Impatience_and_Irritability", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "2dd51aa2f493e55dc06c7a02b62855b89b9098b84e8e557caf51f008f21f6127", "task_id": "emo_Impatience_and_Irritability-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": 0.06525906920433044, "target_z": -0.6406249931934135, "ce": 6.260893821716309, "genuineness": 3.998987913131714, "identity": 0.25359082221984863, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/en/708eb3a96b1672614ea3ccad.mp3" }, { "key": "original-emo_Impatience_and_Irritability-en-0-seed1702-scale0.0", "bucket": "emo_Impatience_and_Irritability", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "85cefc8177fa55f5adc3264d5b4b85622808042e3d9a4f476573ca3a34d7b3e9", "task_id": "emo_Impatience_and_Irritability-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": 0.11336219310760498, "target_z": -0.5703124965967067, "ce": 6.1894097328186035, "genuineness": 4.080576419830322, "identity": 0.004513747990131378, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/en/77ce3926025edd783c38ae78.mp3" }, { "key": "original-emo_Impatience_and_Irritability-en-0-seed1702-scale0.5", "bucket": "emo_Impatience_and_Irritability", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "5426dd7086d893b019cdd33e37d74c590610e926cef2bf5f70dc27fee3e52aa3", "task_id": "emo_Impatience_and_Irritability-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": 0.14810332655906677, "target_z": -0.5195312659954784, "ce": 6.125868320465088, "genuineness": 3.9801597595214844, "identity": 0.40825045108795166, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/en/a131bec59d0b2b1ece34a5eb.mp3" }, { "key": "original-emo_Impatience_and_Irritability-en-0-seed1702-scale0.75", "bucket": "emo_Impatience_and_Irritability", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "776eafec2de9aa388b478089fc775f4fbe8a69442731b40f2be0692ab74f43e4", "task_id": "emo_Impatience_and_Irritability-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": 0.10534501075744629, "target_z": -0.5820312387691322, "ce": 6.308549880981445, "genuineness": 4.093128204345703, "identity": 0.17775316536426544, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/en/54857351060c61ad69e85a91.mp3" }, { "key": "original-emo_Impatience_and_Irritability-en-0-seed1702-scale1.0", "bucket": "emo_Impatience_and_Irritability", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "9b7eac4385ca05d612d9065c0e0e228b2865de61fb9075dd731fc5d1d6754fb3", "task_id": "emo_Impatience_and_Irritability-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": 0.06525906920433044, "target_z": -0.6406249931934135, "ce": 6.173524379730225, "genuineness": 3.9550557136535645, "identity": 0.25003084540367126, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/en/a66f30d6ba233d71b11af26f.mp3" }, { "key": "original-emo_Impatience_and_Irritability-en-1-seed1701-scale0.0", "bucket": "emo_Impatience_and_Irritability", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "31693603af99bfb0727ac1b8b8bd9740ccee730139d525770f09820365b589f3", "task_id": "emo_Impatience_and_Irritability-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.06836074590682983, "target_z": -0.8359375224617357, "ce": 6.300607204437256, "genuineness": 4.394378662109375, "identity": 0.41550350189208984, "hypothesis": "I found the little box. It was beside the old window. We can look inside together,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/en/ec6d71f3f86ea747d0d51731.mp3" }, { "key": "original-emo_Impatience_and_Irritability-en-1-seed1701-scale0.5", "bucket": "emo_Impatience_and_Irritability", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 0.5, "frames_generated": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "258ee6de4e7108141abc416c2deffa7a0483c160577c92349408185eb73ad067", "task_id": "emo_Impatience_and_Irritability-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04387989640235901, "target_z": -0.6718750013613173, "ce": 6.395919322967529, "genuineness": 4.425758361816406, "identity": 0.3935908079147339, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/en/a4811b37817f64983255974d.mp3" }, { "key": "original-emo_Impatience_and_Irritability-en-1-seed1701-scale0.75", "bucket": "emo_Impatience_and_Irritability", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 0.75, "frames_generated": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "8942548a1ed253791d7ba1fd8a190e54a5b1d73240fd7c9d94b8aabde9eeedc3", "task_id": "emo_Impatience_and_Irritability-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.006895601749420166, "target_z": -0.7460937163073965, "ce": 6.2767791748046875, "genuineness": 4.507347106933594, "identity": 0.2835817039012909, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/en/175c77c714df4cc7c0c70321.mp3" }, { "key": "original-emo_Impatience_and_Irritability-en-1-seed1701-scale1.0", "bucket": "emo_Impatience_and_Irritability", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "5651d59b13cdac73f3ebf50607c0a52f7c7b2ae35847bc4e8566d1a943e5d745", "task_id": "emo_Impatience_and_Irritability-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0015508532524108887, "target_z": -0.7382812796086515, "ce": 6.24500846862793, "genuineness": 4.432034492492676, "identity": 0.5849224925041199, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/en/7b4b1b1c9fbd0435279181ca.mp3" }, { "key": "original-emo_Impatience_and_Irritability-en-1-seed1702-scale0.0", "bucket": "emo_Impatience_and_Irritability", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "f5e5fc2b4036cc88a6bff36e36f336bf24d242ba9b056dfca4417c219066d5e5", "task_id": "emo_Impatience_and_Irritability-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.08973991870880127, "target_z": -0.8671875306296395, "ce": 6.2767791748046875, "genuineness": 4.337893962860107, "identity": 0.36200928688049316, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/en/d88b6750a51d58e3dfa0403f.mp3" }, { "key": "original-emo_Impatience_and_Irritability-en-1-seed1702-scale0.5", "bucket": "emo_Impatience_and_Irritability", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "4bd543b0f32ef8e0a9c9327e0c3c376e92a1483a6b131c57d84fc4219893a109", "task_id": "emo_Impatience_and_Irritability-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.05232638120651245, "target_z": -0.8125000381168848, "ce": 6.3641486167907715, "genuineness": 4.356721878051758, "identity": 0.37772083282470703, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/en/d75405d7fd0ec40e942c3c43.mp3" }, { "key": "original-emo_Impatience_and_Irritability-en-1-seed1702-scale0.75", "bucket": "emo_Impatience_and_Irritability", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "9fc1c08997bc3dbb35555f77a5de94ffcf0990008402043563045fdac95913bd", "task_id": "emo_Impatience_and_Irritability-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.05499875545501709, "target_z": -0.8164062564662572, "ce": 6.419747352600098, "genuineness": 4.369274139404297, "identity": 0.28412678837776184, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/en/2ac77bcbe324bacf6509215f.mp3" }, { "key": "original-emo_Impatience_and_Irritability-en-1-seed1702-scale1.0", "bucket": "emo_Impatience_and_Irritability", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "dc8caa79f3b4d43b92ab51c24e220b6e62333aaeeef171f6ad99218184edfdce", "task_id": "emo_Impatience_and_Irritability-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can look inside together.", "original_audio_reused": true, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.06034356355667114, "target_z": -0.8242187802893102, "ce": 6.221180438995361, "genuineness": 4.432034492492676, "identity": 0.4336298704147339, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/en/5248d9a0906b14510245c7cf.mp3" }, { "key": "original-emo_Impatience_and_Irritability-es-0-seed1701-scale0.0", "bucket": "emo_Impatience_and_Irritability", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "c86993a494acd8b1a5529ea790a02f2eb209881a031ca08dd016b78a717073a9", "task_id": "emo_Impatience_and_Irritability-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": 0.12939655780792236, "target_z": -0.5468750122518559, "ce": 6.109982967376709, "genuineness": 4.086852550506592, "identity": 0.6050090193748474, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/es/0d476188d497a58d50f2053a.mp3" }, { "key": "original-emo_Impatience_and_Irritability-es-0-seed1701-scale0.5", "bucket": "emo_Impatience_and_Irritability", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "615da545f1e9b28415fa7b988c83bb847f02c19272657b73b55002e4ab3bdc50", "task_id": "emo_Impatience_and_Irritability-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": 0.15612053871154785, "target_z": -0.507812480260899, "ce": 5.831989288330078, "genuineness": 4.118232727050781, "identity": 0.5454780459403992, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/es/8a130193f0d8f4fdbc39b843.mp3" }, { "key": "original-emo_Impatience_and_Irritability-es-0-seed1701-scale0.75", "bucket": "emo_Impatience_and_Irritability", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "b73935aceea6658df086d9129c5db1f00b13f551d37ec5d4a2fc1062eea9fd1b", "task_id": "emo_Impatience_and_Irritability-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": 0.13474136590957642, "target_z": -0.5390624884288029, "ce": 6.09409761428833, "genuineness": 4.287685871124268, "identity": 0.49833011627197266, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/es/b40c90f2840c50a48f556413.mp3" }, { "key": "original-emo_Impatience_and_Irritability-es-0-seed1701-scale1.0", "bucket": "emo_Impatience_and_Irritability", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "4d98e816576b1aff2611a74ba086a17cbe3802841c9ab6439336157c490ae9fe", "task_id": "emo_Impatience_and_Irritability-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": 0.25499916076660156, "target_z": -0.36328126871811306, "ce": 6.221180438995361, "genuineness": 4.532451152801514, "identity": 0.6237446069717407, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/es/c112d45a55352cca505191cc.mp3" }, { "key": "original-emo_Impatience_and_Irritability-es-0-seed1702-scale0.0", "bucket": "emo_Impatience_and_Irritability", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "d3b01e00e05ff1e6b795bfe0b21fab1b7d16d0e714bd78f40f23641064168815", "task_id": "emo_Impatience_and_Irritability-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": 0.09198302030563354, "target_z": -0.6015625047646106, "ce": 5.847874641418457, "genuineness": 4.011539936065674, "identity": 0.5358524322509766, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/es/7b51269ea3e5555af1473527.mp3" }, { "key": "original-emo_Impatience_and_Irritability-es-0-seed1702-scale0.5", "bucket": "emo_Impatience_and_Irritability", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "b1d943b605bd3f03344d9e3841e064907142098e083c7ba452984193b0d55cca", "task_id": "emo_Impatience_and_Irritability-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": 0.10534501075744629, "target_z": -0.5820312387691322, "ce": 5.982900142669678, "genuineness": 3.7040140628814697, "identity": 0.5368841886520386, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/es/640a2ac08ef1c209974c840e.mp3" }, { "key": "original-emo_Impatience_and_Irritability-es-0-seed1702-scale0.75", "bucket": "emo_Impatience_and_Irritability", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "db136e57a7cb86f33a80d26abe653d002388c50eec2dca36fc7bb6a7ac8a8e3a", "task_id": "emo_Impatience_and_Irritability-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": 0.1240517795085907, "target_z": -0.5546874925127547, "ce": 6.149696350097656, "genuineness": 4.306513786315918, "identity": 0.6404032707214355, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/es/6709dcfdccc065430de0d517.mp3" }, { "key": "original-emo_Impatience_and_Irritability-es-0-seed1702-scale1.0", "bucket": "emo_Impatience_and_Irritability", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "02d3f203965a93affc6aa424e78faab07a34156577fa7b0cef51e1a65e0d9454", "task_id": "emo_Impatience_and_Irritability-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": 0.11870697140693665, "target_z": -0.5625000163358077, "ce": 5.839932441711426, "genuineness": 4.243753433227539, "identity": 0.700171709060669, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/es/d5be345954fbd697a67795cd.mp3" }, { "key": "original-emo_Impatience_and_Irritability-es-1-seed1701-scale0.0", "bucket": "emo_Impatience_and_Irritability", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "defd7201296ad93a33b6ba84a96e1e87aca7e7b20af19032f434e8ab8ba0dd93", "task_id": "emo_Impatience_and_Irritability-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": 0.038535118103027344, "target_z": -0.6796874816222163, "ce": 6.24500846862793, "genuineness": 4.607763767242432, "identity": 0.6122241020202637, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/es/80fd7e153804d43383b4b8c2.mp3" }, { "key": "original-emo_Impatience_and_Irritability-es-1-seed1701-scale0.5", "bucket": "emo_Impatience_and_Irritability", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "4bda74ebfa7623e0ab4f128d26fb4942ec0acbfa34b5cf5169b56aa991e730e2", "task_id": "emo_Impatience_and_Irritability-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": 0.05991426110267639, "target_z": -0.6484375170164665, "ce": 6.09409761428833, "genuineness": 4.770940780639648, "identity": 0.7249748706817627, "hypothesis": "He encontrado la encontrado la cajita. Estaba junto junto a la ventana vieja. 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/audio/emo_Impatience_and_Irritability/es/198ff70c21f93b20e2ba5b7d.mp3" }, { "key": "original-emo_Impatience_and_Irritability-es-1-seed1701-scale0.75", "bucket": "emo_Impatience_and_Irritability", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "afd1a1455892b76b32835ba4789af1e5377c8823d33d3df3840ec1ab92779f3f", "task_id": "emo_Impatience_and_Irritability-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": 0.10801738500595093, "target_z": -0.5781250204197597, "ce": 5.982900142669678, "genuineness": 4.720732688903809, "identity": 0.6560296416282654, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/es/32fb6b22a13916e2a1c02ae1.mp3" }, { "key": "original-emo_Impatience_and_Irritability-es-1-seed1701-scale1.0", "bucket": "emo_Impatience_and_Irritability", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "9e4bb899123c9cfec1a0d5893d0cfa7b8bd8ba2e98f62149ea877acacb8207f2", "task_id": "emo_Impatience_and_Irritability-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": 0.05456948280334473, "target_z": -0.6562499972773653, "ce": 6.181467056274414, "genuineness": 4.344170093536377, "identity": 0.6193814873695374, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/es/88467e295ccd28190db3c009.mp3" }, { "key": "original-emo_Impatience_and_Irritability-es-1-seed1702-scale0.0", "bucket": "emo_Impatience_and_Irritability", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "cd7085e8062b18393e7ad2cbe67d291046e762986c44a1b6c4f7acadf1e428ad", "task_id": "emo_Impatience_and_Irritability-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": 0.05991426110267639, "target_z": -0.6484375170164665, "ce": 6.24500846862793, "genuineness": 4.532451152801514, "identity": 0.6723798513412476, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/es/b7a11e53cfa9499b22bee885.mp3" }, { "key": "original-emo_Impatience_and_Irritability-es-1-seed1702-scale0.5", "bucket": "emo_Impatience_and_Irritability", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "0ffd302e63c638a9ca37008b400a3ce0ac54f08f11d34b1d6cf5ed5c286357d4", "task_id": "emo_Impatience_and_Irritability-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": 0.0011215806007385254, "target_z": -0.7343749741349711, "ce": 6.157639026641846, "genuineness": 4.381826400756836, "identity": 0.4884607195854187, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/es/de55eea83e101592c0877144.mp3" }, { "key": "original-emo_Impatience_and_Irritability-es-1-seed1702-scale0.75", "bucket": "emo_Impatience_and_Irritability", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "fe17aaf3156d7c3808b6f2636f9ad56a9a90b7ddead9b8aa5253118fa632b41c", "task_id": "emo_Impatience_and_Irritability-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": 0.022500723600387573, "target_z": -0.7031250095292212, "ce": 6.197352409362793, "genuineness": 4.770940780639648, "identity": 0.6189346313476562, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/es/a236ae1b4934f13928788491.mp3" }, { "key": "original-emo_Impatience_and_Irritability-es-1-seed1702-scale1.0", "bucket": "emo_Impatience_and_Irritability", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "93cf0331d9376c5384b3e46616b2a0fb83f94c65a2b1020ce40c4847cd214cde", "task_id": "emo_Impatience_and_Irritability-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": 0.022500723600387573, "target_z": -0.7031250095292212, "ce": 6.205295085906982, "genuineness": 4.432034492492676, "identity": 0.472593754529953, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/es/aece5fa08fe3cad39014715c.mp3" }, { "key": "original-emo_Impatience_and_Irritability-fr-0-seed1701-scale0.0", "bucket": "emo_Impatience_and_Irritability", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "5ac2682476b040b2c7838d24c551a3df6df4c81afac2215428dade12b0db9f97", "task_id": "emo_Impatience_and_Irritability-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": 0.116034597158432, "target_z": -0.5664062346851803, "ce": 6.284721851348877, "genuineness": 4.507347106933594, "identity": 0.572430431842804, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/fr/9dc0a07261681be86d78ba7c.mp3" }, { "key": "original-emo_Impatience_and_Irritability-fr-0-seed1701-scale0.5", "bucket": "emo_Impatience_and_Irritability", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "aa909eeae67fa8411b9c24c285c1feaeccde83ca02aea5fa32d53f21174776ab", "task_id": "emo_Impatience_and_Irritability-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": 0.09198302030563354, "target_z": -0.6015625047646106, "ce": 6.141753673553467, "genuineness": 4.356721878051758, "identity": 0.7214878797531128, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/fr/5b4d55512d4264c5f8db0749.mp3" }, { "key": "original-emo_Impatience_and_Irritability-fr-0-seed1701-scale0.75", "bucket": "emo_Impatience_and_Irritability", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "3fc62e083bc7b113eff4ee20d0d2b8595f5650435f25425ddb09e3effa3c4368", "task_id": "emo_Impatience_and_Irritability-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": 0.1681463122367859, "target_z": -0.4902343670022608, "ce": 6.1020402908325195, "genuineness": 4.293961524963379, "identity": 0.6519420146942139, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/fr/172f91f793f2ec803c8064fd.mp3" }, { "key": "original-emo_Impatience_and_Irritability-fr-0-seed1701-scale1.0", "bucket": "emo_Impatience_and_Irritability", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "e9708b9b92b2497d5b180fba34dd39c1f1c482ba48297b257703f5132276356c", "task_id": "emo_Impatience_and_Irritability-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": 0.11068978905677795, "target_z": -0.5742187585082332, "ce": 6.117925643920898, "genuineness": 4.457139015197754, "identity": 0.7931210398674011, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/fr/e9d74a7876c53bad2b96b0cd.mp3" }, { "key": "original-emo_Impatience_and_Irritability-fr-0-seed1702-scale0.0", "bucket": "emo_Impatience_and_Irritability", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "df4ad1687a3032283c5b6090d31edddc12b3d6478ee0bf483654086e3a1104b0", "task_id": "emo_Impatience_and_Irritability-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": 0.1587929129600525, "target_z": -0.5039062619115264, "ce": 6.054384231567383, "genuineness": 4.300237655639648, "identity": 0.8001967668533325, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt ?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/fr/7418fc019d12ce0360791d62.mp3" }, { "key": "original-emo_Impatience_and_Irritability-fr-0-seed1702-scale0.5", "bucket": "emo_Impatience_and_Irritability", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "d34c30e0e7c5f7fd1505edf82828ea20fb69bef48acdb5a04855580efe3e602e", "task_id": "emo_Impatience_and_Irritability-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": 0.07594865560531616, "target_z": -0.6249999891094615, "ce": 6.205295085906982, "genuineness": 4.494794845581055, "identity": 0.5782595872879028, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/fr/77f264d46b809062aa7d8e2d.mp3" }, { "key": "original-emo_Impatience_and_Irritability-fr-0-seed1702-scale0.75", "bucket": "emo_Impatience_and_Irritability", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "327daebb556695a731f606c6f9d539356c65b7fc9b1258bad191a08fd2ecc7bf", "task_id": "emo_Impatience_and_Irritability-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": 0.18818926811218262, "target_z": -0.46093751157119717, "ce": 5.998785495758057, "genuineness": 4.419482707977295, "identity": 0.6094967722892761, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/fr/c6642daf85d36f827f1176d0.mp3" }, { "key": "original-emo_Impatience_and_Irritability-fr-0-seed1702-scale1.0", "bucket": "emo_Impatience_and_Irritability", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1702, "scale": 1.0, "frames_generated": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "1f0aeadeff5213286b4b67ac7552cc710704b6ef6336772ef537aad1b94b0e51", "task_id": "emo_Impatience_and_Irritability-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": 0.1427585482597351, "target_z": -0.5273437462563774, "ce": 6.316492557525635, "genuineness": 4.319066047668457, "identity": 0.7315998077392578, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt. Dis-moi quand tu es prêt.", "wer": 0.3333333333333333, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/fr/635725fcea5e2676bd18b28b.mp3" }, { "key": "original-emo_Impatience_and_Irritability-fr-1-seed1701-scale0.0", "bucket": "emo_Impatience_and_Irritability", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "3a94d49f89bb3539b70e0aa1a112b41534a0dcaff3d86316d3c44ef4c3bfd3cb", "task_id": "emo_Impatience_and_Irritability-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": 0.05456948280334473, "target_z": -0.6562499972773653, "ce": 6.1020402908325195, "genuineness": 4.595211505889893, "identity": 0.7604994177818298, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/fr/b8ef70d8e24bd17ed3a78b1c.mp3" }, { "key": "original-emo_Impatience_and_Irritability-fr-1-seed1701-scale0.5", "bucket": "emo_Impatience_and_Irritability", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "30802bd0e5a5ca368df00b06bff271a3f7c23319e220bbfc709e629e096b78ce", "task_id": "emo_Impatience_and_Irritability-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": 0.009138762950897217, "target_z": -0.7226562319625456, "ce": 6.2767791748046875, "genuineness": 4.457139015197754, "identity": 0.8703855276107788, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/fr/435d2ce1c9846507c4e4e00b.mp3" }, { "key": "original-emo_Impatience_and_Irritability-fr-1-seed1701-scale0.75", "bucket": "emo_Impatience_and_Irritability", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "70f299063e97edb3943059fd73fdfb9820488db8ee175b017ad0364a4fd25e84", "task_id": "emo_Impatience_and_Irritability-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": 0.00646635890007019, "target_z": -0.7265624938740721, "ce": 6.09409761428833, "genuineness": 4.545003414154053, "identity": 0.792471170425415, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/fr/21f7389abd46ceca21f51029.mp3" }, { "key": "original-emo_Impatience_and_Irritability-fr-1-seed1701-scale1.0", "bucket": "emo_Impatience_and_Irritability", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "093a992c13ac5b7a8cdb4af5d7c058772a4cd66ff90c419289410668d9bc74ca", "task_id": "emo_Impatience_and_Irritability-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": 0.12137937545776367, "target_z": -0.5585937544242813, "ce": 5.998785495758057, "genuineness": 4.469690799713135, "identity": 0.7689679861068726, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/fr/ee9e42a994270f17c66dc475.mp3" }, { "key": "original-emo_Impatience_and_Irritability-fr-1-seed1702-scale0.0", "bucket": "emo_Impatience_and_Irritability", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "09f6c020a724eac7b748ea683ba8ef37457152db5881cce96a7313fa2817be62", "task_id": "emo_Impatience_and_Irritability-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": -0.00956803560256958, "target_z": -0.750000021781077, "ce": 6.316492557525635, "genuineness": 4.607763767242432, "identity": 0.824101984500885, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/fr/8723a80d29be43d060d5ce99.mp3" }, { "key": "original-emo_Impatience_and_Irritability-fr-1-seed1702-scale0.5", "bucket": "emo_Impatience_and_Irritability", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "45a90cb9faa06945232a5ff65fe96af96115b84747397b67fea6c7fa23c1aad3", "task_id": "emo_Impatience_and_Irritability-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": -0.0015508532524108887, "target_z": -0.7382812796086515, "ce": 6.070269584655762, "genuineness": 4.369274139404297, "identity": 0.7878024578094482, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/fr/6eabb20c60cfa9be5ba5f8b6.mp3" }, { "key": "original-emo_Impatience_and_Irritability-fr-1-seed1702-scale0.75", "bucket": "emo_Impatience_and_Irritability", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "3d611be1d6fe1092ede2f0b295b5f0e5666257afdec3c2fcb203897752b94245", "task_id": "emo_Impatience_and_Irritability-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": -0.004223227500915527, "target_z": -0.7421874979580241, "ce": 6.23706579208374, "genuineness": 4.532451152801514, "identity": 0.8356080055236816, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/fr/f38625371c57cc1712b10e41.mp3" }, { "key": "original-emo_Impatience_and_Irritability-fr-1-seed1702-scale1.0", "bucket": "emo_Impatience_and_Irritability", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "12023ade8673c053ab240cd0b5c0bdb2e728d2b2b741547cb45eb7fd5c24bcb5", "task_id": "emo_Impatience_and_Irritability-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": 0.08129343390464783, "target_z": -0.6171875088485625, "ce": 6.173524379730225, "genuineness": 4.6203155517578125, "identity": 0.7428983449935913, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/fr/3a8951a570be01f282d777bc.mp3" }, { "key": "original-emo_Impatience_and_Irritability-nl-0-seed1701-scale0.0", "bucket": "emo_Impatience_and_Irritability", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "0845fcba3570a42ab25ed5249a799458c0cb2ef67aab0bf7bdf9f5620b41b472", "task_id": "emo_Impatience_and_Irritability-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": 1.0246491432189941, "target_z": 0.7617186768291945, "ce": 6.046441555023193, "genuineness": 3.9173994064331055, "identity": 0.6311503648757935, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/nl/00b242ad86d14be9cc1d0c82.mp3" }, { "key": "original-emo_Impatience_and_Irritability-nl-0-seed1701-scale0.5", "bucket": "emo_Impatience_and_Irritability", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "f5e3fae52095343a0df520dc959fcf8f7a327299b7f7698c11ee8a85ed41a811", "task_id": "emo_Impatience_and_Irritability-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": 0.9524945020675659, "target_z": 0.6562499972773653, "ce": 6.173524379730225, "genuineness": 4.068024158477783, "identity": 0.5025969743728638, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/nl/c848f09333b3e894ce7e3fde.mp3" }, { "key": "original-emo_Impatience_and_Irritability-nl-0-seed1701-scale0.75", "bucket": "emo_Impatience_and_Irritability", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 0.75, "frames_generated": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "9c94095e03ff20afea1e7f31dd8f22763136c69f1206a1af1b30702b00836843", "task_id": "emo_Impatience_and_Irritability-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": 0.5502989292144775, "target_z": 0.06835938742202048, "ce": 6.221180438995361, "genuineness": 4.293961524963379, "identity": 0.5542882680892944, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/nl/7a36f6e211cd1c9759578305.mp3" }, { "key": "original-emo_Impatience_and_Irritability-nl-0-seed1701-scale1.0", "bucket": "emo_Impatience_and_Irritability", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "53e615d94cafef56424b44feda50eb9924bac01a48533abbd0aaeb15ce1cc9ab", "task_id": "emo_Impatience_and_Irritability-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": 0.32715386152267456, "target_z": -0.257812502041976, "ce": 6.197352409362793, "genuineness": 4.193545341491699, "identity": 0.6083033084869385, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/nl/1da15c72282e8074de20d02b.mp3" }, { "key": "original-emo_Impatience_and_Irritability-nl-0-seed1702-scale0.0", "bucket": "emo_Impatience_and_Irritability", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "74db7b1ba106cf870950f4351f63ed249db3c94930514064ea546ab0397c495e", "task_id": "emo_Impatience_and_Irritability-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": 0.5629928112030029, "target_z": 0.08691407704907878, "ce": 6.054384231567383, "genuineness": 4.162164688110352, "identity": 0.2264275699853897, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/nl/e498c42a8d73e0c64d1ace41.mp3" }, { "key": "original-emo_Impatience_and_Irritability-nl-0-seed1702-scale0.5", "bucket": "emo_Impatience_and_Irritability", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "2de453728dfbfdace6bf8e55e1b0f41d43b73810695d02b3c5d2bbae92c0ffa3", "task_id": "emo_Impatience_and_Irritability-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": 0.22025802731513977, "target_z": -0.41406249931934136, "ce": 6.109982967376709, "genuineness": 4.281409740447998, "identity": 0.6187324523925781, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/nl/70c31323747e42b748b3a3d3.mp3" }, { "key": "original-emo_Impatience_and_Irritability-nl-0-seed1702-scale0.75", "bucket": "emo_Impatience_and_Irritability", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1702, "scale": 0.75, "frames_generated": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "efc385f5463a242cebcf3fc229ba15dfdd11ffe6de48d8ed6c62835290c0cdac", "task_id": "emo_Impatience_and_Irritability-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": 0.3324986696243286, "target_z": -0.249999978218923, "ce": 6.0305562019348145, "genuineness": 4.394378662109375, "identity": 0.5268852114677429, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/nl/ef4016fe5058e31ab803177e.mp3" }, { "key": "original-emo_Impatience_and_Irritability-nl-0-seed1702-scale1.0", "bucket": "emo_Impatience_and_Irritability", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "c5adad8457eb2e418442650521d7b1471f91901bb314a7190d4de23c78e98258", "task_id": "emo_Impatience_and_Irritability-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": 0.4474116861820221, "target_z": -0.08203123876913217, "ce": 6.046441555023193, "genuineness": 4.068024158477783, "identity": 0.6404632329940796, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/nl/57fdd18c24701047fb750d0f.mp3" }, { "key": "original-emo_Impatience_and_Irritability-nl-1-seed1701-scale0.0", "bucket": "emo_Impatience_and_Irritability", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "6cf072d426a28228ce02a6ca252307d56cae55617cddd061dbd1ba130fc12f15", "task_id": "emo_Impatience_and_Irritability-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": 0.18017208576202393, "target_z": -0.47265625374362263, "ce": 6.09409761428833, "genuineness": 4.1998209953308105, "identity": 0.5941785573959351, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/nl/06dceb1b2ab33714977ffef3.mp3" }, { "key": "original-emo_Impatience_and_Irritability-nl-1-seed1701-scale0.5", "bucket": "emo_Impatience_and_Irritability", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "1fd11e65f89f66cf69568c5c6f6af9d576e93d8a355590399f8503e0b204e949", "task_id": "emo_Impatience_and_Irritability-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": 0.18017208576202393, "target_z": -0.47265625374362263, "ce": 6.173524379730225, "genuineness": 4.105680465698242, "identity": 0.7020643949508667, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude graam. We kunnen er samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/nl/1db640ccd54dddacadf17f0b.mp3" }, { "key": "original-emo_Impatience_and_Irritability-nl-1-seed1701-scale0.75", "bucket": "emo_Impatience_and_Irritability", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "0f96d0bfa8c3711ab82f76079f10576893e66c854c8bdb979df9a876f8f6b3fa", "task_id": "emo_Impatience_and_Irritability-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": 0.269697368144989, "target_z": -0.3417968499857944, "ce": 6.133810997009277, "genuineness": 4.375550270080566, "identity": 0.7964807152748108, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/nl/41571f2a12aec73e7dbeced1.mp3" }, { "key": "original-emo_Impatience_and_Irritability-nl-1-seed1701-scale1.0", "bucket": "emo_Impatience_and_Irritability", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "729d32361801bb3d359ef7b944966a349348e118c1e79da04285a1c54d142654", "task_id": "emo_Impatience_and_Irritability-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": 0.2509905695915222, "target_z": -0.36914063980432577, "ce": 6.125868320465088, "genuineness": 4.105680465698242, "identity": 0.6995528340339661, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/nl/08de44ae64cd290ac669272e.mp3" }, { "key": "original-emo_Impatience_and_Irritability-nl-1-seed1702-scale0.0", "bucket": "emo_Impatience_and_Irritability", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "c4dba1fd75ec146386a4065694d0bddceb09eae2da2529fbc7347dc6c12778d0", "task_id": "emo_Impatience_and_Irritability-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": 0.35254162549972534, "target_z": -0.22070312278785936, "ce": 6.24500846862793, "genuineness": 4.3504462242126465, "identity": 0.6224226951599121, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/nl/666cc677d5fa28edee38e849.mp3" }, { "key": "original-emo_Impatience_and_Irritability-nl-1-seed1702-scale0.5", "bucket": "emo_Impatience_and_Irritability", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "550e933aaf97ba470d397d9af147b10387eea5c63c1c0a9e549921680646ed65", "task_id": "emo_Impatience_and_Irritability-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": 0.194870263338089, "target_z": -0.4511718785734579, "ce": 6.205295085906982, "genuineness": 4.356721878051758, "identity": 0.6794472932815552, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/nl/d90c922b495f6a1588ece34d.mp3" }, { "key": "original-emo_Impatience_and_Irritability-nl-1-seed1702-scale0.75", "bucket": "emo_Impatience_and_Irritability", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "3d6ca69a46ef670804064783847541a2467b688db3405b3a6b94e344fac42125", "task_id": "emo_Impatience_and_Irritability-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": 0.42336010932922363, "target_z": -0.11718750884856254, "ce": 6.173524379730225, "genuineness": 4.325342178344727, "identity": 0.5431269407272339, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/nl/0d3610012861aa9c3178138b.mp3" }, { "key": "original-emo_Impatience_and_Irritability-nl-1-seed1702-scale1.0", "bucket": "emo_Impatience_and_Irritability", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "8839c3a271e3407dc3f2b6409b59bf3abd44fe1462b8a80776d3ccc0b07222c4", "mp3_sha256": "79ad7f03baeb4fc4c11aaec15f4b33d4a9c30795a920f4337a86c261e2d6c4df", "task_id": "emo_Impatience_and_Irritability-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Impatience and Irritability. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Impatience and Irritability. 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 Impatience and Irritability. 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 Impatience and Irritability. 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": 0.13474136590957642, "target_z": -0.5390624884288029, "ce": 6.23706579208374, "genuineness": 4.1998209953308105, "identity": 0.5203514695167542, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Impatience_and_Irritability/nl/75c6faa24b5aa859c5666fb3.mp3" } ], "source_standard_audio_unchanged": true }